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

Annotations already cover the safety profile (destructiveHint=false, openWorldHint=true), and the description reinforces the external dependency by naming 'an available public ad library.' It adds no rate-limit, quota, auth, or result-count context, and 'Find' sits in mild tension with readOnlyHint=false (a query tool flagged as non-read-only), though that is likely a metering side effect rather than a true contradiction.

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 short, front-loaded sentences with no filler; the action and scope lead. The second clause ('returns IDs for a user-selected watch') is slightly cryptic jargon that costs a little clarity, but the definition remains tight.

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 detail is rightly omitted. Given three required parameters at zero schema coverage and a third-party data source with plausible rate limits, the description is adequate but leaves the brandId input and any operational caveats unexplained.

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% for all three required parameters. The description only obliquely covers two of them: 'by name' maps to query and 'Meta or TikTok' restates the source enum already visible in the schema. The required brandId parameter is never mentioned in the description and is entirely undocumented anywhere.

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 and resource: 'Find public Meta or TikTok advertisers by name.' This is clearly distinct from siblings like search_library_ads (ads, not advertisers) and create_ad_watch (which consumes the returned IDs). It stops short of explicitly naming the sibling boundary, which keeps it at a 4 rather than a 5.

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 phrase 'returns IDs for a user-selected watch' implies a downstream workflow (feed the IDs into create_ad_watch), which is helpful implied usage. However, there is no explicit statement of when to use this versus search_library_ads, nor any prerequisite or exclusion. Guidance is inferable but not stated.

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