find_similar_builds

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

The description discloses that returned records include full prompt/tool-call/outcome details and warns that dimensions, names, and positions may differ. It does not explicitly state read-only behavior, but 'search' implies non-mutating. Given no annotations, this is a reasonable level of transparency.

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?

The description is well-structured and efficient: a one-sentence purpose, a returns statement with caveats, usage guidance, and a clear Args section. Every sentence adds value, and information is front-loaded.

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?

The tool is a search/reference operation with an output schema, and the description sufficiently explains what is returned, the limitations of results, and when to use it mid-build. It is complete for an agent to select and invoke 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?

The schema provides no parameter descriptions (0% coverage), but the description fully compensates: query is defined as 'a natural-language description of what you're building' and top_k as 'maximum number of examples to return (default 3).' This adds essential meaning beyond the schema.

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?

The description clearly states the tool's action: 'Search the verified-build corpus for prior examples similar to a request.' It identifies a distinct resource and function, and differentiates from siblings by framing it as a reference tool, specifically mentioning begin_build.

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?

It provides explicit usage context: 'Useful to call again mid-build for a specific sub-assembly, not just once via begin_build,' directly contrasting with a sibling tool. It also advises using results as reference rather than copying mechanically, which clarifies appropriate use.

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