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

Beyond the annotations (readOnly, idempotent), the description discloses the version limitation and the specific behavior for invalid ids (returns uncited(out_of_scope) instead of an error). It also hints at future capabilities. This adds value beyond the annotations without contradicting them.

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 overlong and includes a misleading example: 'call introspection_corpus_compare with arguments {}' suggests calling with no arguments, but the schema requires two required parameters. This could confuse an agent. The version-note and future plans add noise; the key information could be conveyed in two concise sentences.

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?

Given the simple tool (2 string params, read-only, idempotent) and existing annotations, the description provides essential constraints (valid id, behavior for invalid ids) but leaves out what the 'comparison' result looks like. Since there is no output schema, a brief example or format hint would help, but the description is adequate for a limited tool.

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 descriptions and the description does not elaborate on the meaning of corpus_id_a and corpus_id_b beyond calling them 'ids' and stating 'current' is the only valid value. It implies both should be set to 'current', but does not explain what the comparison entails or how the two parameters relate. Since schema coverage is 0%, the description compensates only partially.

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 'Compare two corpora by id' - a specific verb and resource that distinguishes this from sibling tools like introspection_corpus_generate or introspection_corpus_query. It also clarifies the version context and the scope of valid ids, making its purpose unambiguous.

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 description provides explicit usage guidance: only the literal string 'current' is valid, and passing it for both sides is the intended sanity-check usage. It also explains that other ids return uncited(out_of_scope) rather than an error. However, it does not explicitly recommend when to use this tool over alternatives, though the context implicitly frames it as a testing/validation tool.

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