part_fetch

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

With no annotations, the description carries the full burden and does so: provider is never inferred and a bare id is refused, the provider argument overrides a prefix, download_dir writes to disk and is off by default, and downloaded files are validated against the local KiCad with newer s-expression formats surfaced as *_warning rather than a clean result. These are non-obvious failure and side-effect behaviours an agent could not infer.

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 ref contract are front-loaded, and the ordering (ref, provider, download_dir, validation, returns) follows the call sequence. Some editorialising ('guessing is how one source quietly becomes the answer to everything') is longer than needed but does reinforce the refusal behaviour.

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?

For a three-parameter fetch with an output schema present, the description covers input contract, precedence rules, side effects, error/warning behaviour, and even summarises the return envelope. Nothing needed to invoke it correctly is missing.

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 coverage is 0%, so the description must supply all parameter meaning, and it does: part_id is defined as a provider:part_id ref, provider is described as optional and precedence-bearing over a prefix, and download_dir is described as an opt-in disk write. All three parameters gain semantics absent from 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?

Opens with a specific verb and resource ('Fetch one part's detail') and immediately scopes it to the ref returned by a search, which distinguishes it from the sibling part_search that produces those refs. An agent can pick between the two without opening either schema.

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 instructs passing the ref straight through and notes part_search emits a ref on every hit, which is clear routing guidance. It stops short of an explicit 'call part_search first if you lack a ref' exclusion, but the workflow is unambiguous.

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