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

Beyond the readOnly/idempotent annotations, it discloses non-obvious behavior: a failed job still returns HTTP 200 with a structured error, partial results remain readable, and counts have specific semantics (unique identities including failed/skipped reads; saved does not mean newly created). It also states the required outreach:read scope, which no annotation conveys.

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?

Dense and front-loaded: the aggregate/polling model comes first, then failure semantics, then counts, then auth. The opening line duplicates the title verbatim, which is the only real waste; the remaining sentences each carry distinct operational information.

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 polling-status tool with an output schema already present, the description covers the hard parts an agent would otherwise guess at: terminal states, partial-result readability, error-vs-HTTP-status behavior, count semantics, and required scope. Nothing needed 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?

The schema nests a single path.companySearchId parameter with minimal top-level documentation (0% coverage), and the description compensates partly by stressing 'No task IDs are exposed', reinforcing that a public resource ID is expected. It adds meaning about ID identity but nothing about the nested 'path' wrapper or format beyond the schema's uuid hint.

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 states a specific verb and resource ('Get company search status', 'One aggregate owns every child scan') and makes clear this is a polling endpoint for an aggregate job rather than a results reader. The mention of companiesDiscovered/companiesSaved counts further distinguishes it from listCompanySearchResults, though it never names that sibling explicitly.

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?

'Poll until completed, failed or cancelled, or subscribe to terminal webhooks' gives an explicit usage pattern and a stated alternative mechanism. It stops short of naming the sibling tools (e.g. listCompanySearchResults for the actual profiles) that an agent would need once the job completes.

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