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

Annotations only declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, and openWorldHint=false; the description goes well beyond that by disclosing the caching model, the 'cached: true' marker on repeat calls, the cost (one of the account's daily Ad Spy lookups, consisting of a video transcript plus one AI call), and the plan/auth prerequisites. It also sets a scope boundary — no invented metrics — so the agent knows the analysis is grounded in the ad's actual content.

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?

Front-loaded with the WRITE label and the output contents, then cost/caching, then prerequisites — a sensible ordering that matches how an agent decides and executes. It is dense but every clause carries operational information; the only minor cost is the length of the parenthetical describing the lookup's composition.

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 one-parameter tool with no output schema, the description covers everything an agent needs: what is produced, what an existing cached entry looks like in the response, what the call costs, and what entitlements are required. The absence of an output schema is compensated by the enumerated result fields.

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?

There is a single parameter and schema description coverage is 100%, with the schema itself clarifying that creative_id is the Sonar ad id from sonar_ad_spy_ads rather than the Meta ad_id. The description adds no additional parameter guidance, so the baseline of 3 applies — the schema carries the load.

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 (analyze/generate a breakdown) and resource (a competitor ad) and enumerates the concrete output sections: hook, persuasion angle, creative format, beat-by-beat structure, CTA, and a grounded 'why it works'. It explicitly labels itself a WRITE tool, distinguishing it from the sibling sonar_ad_spy_ad_analysis, which by name reads as a retrieval counterpart.

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 clear qualifying conditions — requires an Indie/Agency plan (trial counts) and an authorized account or write-scoped API key — plus the practical rule that already-cached ads come back free instead of consuming a lookup. It does not explicitly name sonar_ad_spy_ad_analysis as the cheaper read path, so the routing to that sibling is left inferable rather than stated.

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