start_search

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

Annotations declare readOnlyHint=false and openWorldHint=true, so the write/external nature is known; the description reinforces this by stating it creates a run. It also discloses the running-state behavior that triggers resume_search rather than a second start_search, which is genuine context beyond the annotations. It doesn't say what happens on re-invocation or failure, so not a 5.

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 tightly written sentences, front-loaded with the core action and side effect, with the conditional follow-up second. No wasted words.

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 values need no explanation, and the mutation/routing behavior is covered. The only shortfall is the undocumented wait_seconds and limit_per_source, which leaves an agent guessing on latency and result volume.

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 only 50%: project and question_id are documented, but wait_seconds and limit_per_source have no description anywhere. The description only hints at the 'approved question' notion and says nothing about the wait/limit tuning knobs, so it fails to compensate for the coverage gap.

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?

States a specific verb (search) and resource (literature databases) and adds the important side effect that it creates a run in the project. It does not name sibling boundaries beyond resume_search, but an agent can distinguish it from list_articles/fetch_articles. Clear but not fully differentiated from the broader sibling set.

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?

Gives a precondition (an approved question) and an explicit alternative path: when search_status is 'running', call resume_search(run_id) instead. That is concrete when-to-use guidance, though it lacks explicit when-not-to-use conditions or rate/cost caveats.

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