Borrowing it
Nothing to install: this file belongs to buildkite/buildkite-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/buildkite/buildkite-mcp-server/main/.agents/skills/tool-parameter-descriptions/SKILL.mdgit clone --depth 1 https://github.com/buildkite/buildkite-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/buildkite/buildkite-mcp-server/tool-parameter-descriptions)<a href="https://agentmods.dev/skills/buildkite/buildkite-mcp-server/tool-parameter-descriptions"><img src="https://agentmods.dev/badge/skills/buildkite/buildkite-mcp-server/tool-parameter-descriptions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/buildkite/buildkite-mcp-server/tool-parameter-descriptions"><img src="https://agentmods.dev/badge/skills/buildkite/buildkite-mcp-server/tool-parameter-descriptions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00024 | $0.00429 |
| Opus 5.5 | $0.00010 | $0.00172 |
| Sonnet 5.5 | $0.00005 | $0.00086 |
| Haiku 4.5 | $0.00002 | $0.00043 |
Grade A, and why
tool-parameter-descriptions scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tool Parameter Descriptions
Use these guidelines when adding or reviewing MCP tool input schemas.
Standard
A parameter description must add information that cannot be recovered from the parameter name, JSON type, required status, or tool description.
Keep a description when it communicates at least one of:
- Accepted values, syntax, units, bounds, or defaults.
- Dependencies or mutual exclusion with other parameters.
- Behavior when omitted or set to a sentinel value such as zero.
- Replacement, destructive, or other side effects.
- Identifier type or source when similar identifiers are easily confused.
- Non-obvious filtering or matching behavior.
Otherwise, omit it. In particular, do not:
- Restate the parameter name, such as
build_number: "Build number". - Say that a parameter is optional when the schema already expresses that.
- Repeat information already provided by the tool description.
- Add generic domain explanation that does not affect the argument value.
Prefer short phrases over complete sentences. Put machine-readable constraints such as enums, bounds, and defaults in the schema when supported; use prose only for information the schema cannot express clearly.
Review
Read the handler as well as the parameter type. Check defaults, validation, identifier formats, coupled parameters, pagination behavior, and side effects before deciding whether a description is needed.
Use this deletion test: if removing the description would not make a materially different or invalid tool call more likely, remove it.
Examples:
- Omit
Description of the clusterfromdescription. - Replace
Build numberwithSequential build number, not the build UUIDwhen that distinction matters. - Use
Maximum matches to return; 0 returns allfor a limit with non-obvious zero behavior. - Preserve warnings such as an update replacing an entire map.
Update schema tests for behaviorally important descriptions and run the relevant Go tests. Use LLM evals for changes intended to improve tool selection or argument construction; unit tests cannot establish model effectiveness.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 46 lines · 24 tokens per session scan A 1be5ef0bcce6
tool-parameter-descriptions is a skill published in the GitHub repository buildkite/buildkite-mcp-server (56 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 429 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
ue-mcp-epic-routing
Use when deciding between ue-mcp's native category actions and Epic's wrapped ToolsetRegistry tools (the epic actions, incl. the Blueprint graph DSL) for a task in Unreal. Pulls in when authoring Blueprint graph bodies, or any time both a native action and an epic action could do the job and you need to pick.
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.
apitap
ApiTap gives AI agents cheap access to web data through three layers.
frontmcp-setup
Use when starting, scaffolding, or organizing a FrontMCP project. Covers creating a new project (CLI scaffold or manual) for Node, Vercel, and other targets; standalone versus Nx-monorepo layout, naming conventions, generators, and dependency rules; composing multiple @App classes, ESM packages, and remote MCP servers…