Run the app audit

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

Annotations only flag that this is a non-idempotent, non-destructive, open-world write. The description adds the behavior an agent actually needs: it is queued rather than synchronous, results are written per country as they finish, countries omitted from the list retain their prior audit, an interrupted run resumes after restart, and the main country is processed first. That is substantial disclosure well beyond the annotation surface.

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 core action is front-loaded in the first clause and every subsequent clause carries information. It is a single long run-on sentence with comma-chained subclauses, which slightly hurts scanability, but almost nothing could be removed without losing meaning.

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 non-idempotent, no-output-schema job tool, the description covers execution order, partial-result persistence, resume behavior, and the follow-up calls needed to collect results. The one gap is what happens if the tool is called again while a run is already queued, which matters given idempotentHint=false.

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?

With only 50% schema coverage and a nested options object, the description earns its keep by explaining refetch, moreKeywords (steered by note, else toward main competitors), note, recheck, and the default for countries (untouched countries keep their last audit). The ai provider option and useAi=false are left to the schema, so it is strong but not exhaustive.

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?

"Queue an audit run" gives a specific verb and resource, then enumerates the pipeline it kicks off: refetch, keyword research, phrase checks, per-country AI conclusions, and a cross-country summary. An agent can immediately tell this apart from get_audit (retrieval) and wait_for_jobs (polling).

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 explicitly routes the agent onward with "Then wait_for_jobs and get_audit," which is real sequencing guidance against named siblings. It does not state when NOT to run an audit (e.g., cost/time trade-offs versus run_rank_check or re-running when an audit already runs), so it stops short of full exclusion guidance.

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