find_tools

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered; the description still adds real context beyond that: it searches GitHub AND the Legwork cache, returns selection facts (stars, license, freshness, cached, already has an MCP server), and explicitly states no installation occurs. Only the pagination/result-count behavior is left unspecified.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and the local-file trigger are front-loaded, and the sandbox-vs-local-machine contrast justifies the tool's existence rather than padding. It runs slightly long, with the second sentence restating the local-file rationale already implied by the path examples.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, yet the description compensates by naming the facts returned (stars, license, freshness, cached, MCP-server availability) and the two search sources. Combined with the when-to-use guidance and the no-install guarantee, an agent has everything needed to call this correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single query parameter already documents the 2-3 keyword format and filler-word caveat. The description adds only the provenance context (GitHub vs Legwork cache) that explains why keywords must match literally, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (find) and resource (a tool that runs on the user's own computer) and immediately scopes it to jobs the agent has no tool for, with concrete example tasks (transcribe audio, pull tables from a PDF). This is clearly distinguishable from install_tool/use_tool/list_installed_tools in the sibling set.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly frames when to reach for it (no existing tool for the job, especially local-file work with example paths like ~/Downloads/memo.m4a), and implicitly excludes the cloud sandbox route by explaining it cannot see unattached user files. 'Installs nothing' also routes the agent to install_tool for the follow-up step.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.