report_competitor_deep

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

No annotations are provided, so the description carries the full transparency burden. It explicitly discloses that captured changes are inferred with low confidence, SensorTower data are estimates, and unobservable data is skipped rather than guessed. These are important trust hypotheses for an agent.

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?

Single dense sentence that is front-loaded with the core differentiator ('ONE competitor'), lists output section markers, and ends in a concise policy about data limitations. No filler or redundant restatement.

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?

Without an output schema or annotations, the description still names all major report sections and explains the tool's limits. It does not describe the output dossier's structure, but the provided parameter schema and section enumeration are enough for an agent to invoke the tool correctly.

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?

At 60% schema description coverage, the description adds meaningful context by linking the conceptual workflow to the parameters: competitor to competitorAppId, keyword portfolio to terms, and to ownAppId. It does not specifically explain maxReviewPages or storefront, but those are more self-explanatory and partially covered by the schema.

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?

Opens with 'Deep-dive on ONE competitor' and precisely enumerates what the tool produces: listing profile, inferred changes, monetization signals, keyword portfolio against own ranks, and complaint mining. This clearly distinguishes it from report_app and report_comparison.

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 'ONE competitor' language gives clear context and the sibling-tool naming for report_comparison implies the multi-competitor alternative. The 'everything is public data' caveat and 'skipped, not guessed' note also set agent expectations. It does not explicitly name an alternative or state a hard exclusion, so it stops short of a 5.

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