Check parts before rebuilding

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

Beyond the readOnlyHint annotation, the definition adds real behavioral context: it does not write any output file, ok is false when something is wrong, and the missing_parts, missing_names, and corrupt_parts fields name the specific parts. The rule "A part that fails its SHA-256 is corrupt, not missing" resolves an ambiguity in error classification that the schema and annotations cannot express.

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?

Five short sentences, with the purpose first, then the scope exclusions, then the supported formats, then the failure semantics. Every sentence adds information, and none is filler or redundant.

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 tool that verifies multi-part files across formats and has an output schema, this covers the format matrix, the fact that it is read-only, and the structure of the error and partial fields. Nothing an agent needs in order to call 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 100% and the parts parameter already documents its accepted forms, including the single-string case. The description adds only indirect support through the manifest filenames, without expanding on the path forms. Under those conditions, a baseline 3 applies.

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 opening sentence names the operation and resource ("Confirms every part is present and each part's checksum matches the manifest"), which is a specific statement of intent. The later sentence "Does not write a rebuilt file" cleanly separates this tool from rebuild and from a plain inspect.

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?

The phrase "Read-only check before rebuild" sets the situation clearly, and the supported manifest formats tell the agent when the tool applies. However, it never points to a sibling by name (inspect, rebuild, regenerate_parts) as an alternative, nor does it state any case where it should not be used.

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