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

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, and the description reinforces this by promising no retrieval/acquisition and no generated answers. It adds genuinely useful output-shape context: results are gap suggestions, not evidence, which sets expectations the annotations cannot convey. Auth, rate-limit and latency behavior remain unstated.

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?

Two tight sentences, purpose front-loaded, with the scope exclusions compressed into one semicolon clause. Nothing is redundant and nothing needs to be re-read.

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?

An output schema exists, so return-value description is rightfully omitted, and the behavioral boundaries are covered well enough to call the tool safely. The single material hole is the undocumented 'source_ids' parameter, which an agent needs to decide whether to pass.

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 0% and the description never mentions the parameters. The 'question' argument is self-evident, but 'source_ids' (bounded to 4 ids matching ^public-pg-[0-9]+$) is completely unexplained — an agent cannot tell whether it scopes the gap search, supplies known sources, or seeds the analysis.

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 names a specific verb and resource: it identifies corpus limitations and the kinds of evidence a question would need, specifically when the question is unsupported. The closing clause ('suggestions are gaps, never retrieved evidence') draws a hard line against the retrieval siblings (retrieve_evidence, search_library), so an agent can route 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?

It states the triggering condition clearly — use this for an unsupported question where evidence is lacking — and enumerates what it will not do (no web search, acquisition, factual answer, personalized advice). It never names a sibling tool as the alternative for those excluded cases, so the routing is implied rather than explicit.

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