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

Though annotations already cover read-only/destructive/idempotent hints, the description adds substantial behavioral context: it creates billable AI usage, supports validate_only/preview_only/execute mutation modes, has a partial failure policy, returns internal application state, and derives deterministic retry keys. This goes well beyond what the annotations provide.

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 purpose is front-loaded and clear, but the description then includes a dense block of generic operational policy (classification, execution, task support, mutation modes, partial failure policy, output formatting) that could be more compact or structured. Each sentence has value, but the overall text is longer than needed.

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 tool with 25 parameters, zero schema description coverage, and numerous near-duplicate fields, the description is not complete enough for correct invocation. It does not explain which identifier to use, whether fields are alternatives or required, or how markets/targetMarkets and strategyMode/strategyModes relate. The output schema and annotations help, but the input selection semantics remain under-specified.

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 25 parameters and 0% schema description coverage, the description carries a heavy burden but only clarifies forceRefresh, the 90-day default, and DISPLAY evidence mode. It does not explain the relationships between advertiserId/competitorId and name/domain alternatives, nor the market/markets and strategyMode/strategyModes duplication, so the agent cannot confidently map all parameters.

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 opens with a specific verb and resource: 'Run canonical LeanrIQ Competitor Intelligence V2 for one advertiser-scoped competitor.' It also clarifies the scoping and default behavior, and explicitly marks the tool as a deprecated alias for run_competitor_intelligence, which distinguishes it from siblings.

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 tells the agent that this is a deprecated alias for run_competitor_intelligence, which is a clear routing instruction. It also states when cached results are reused ('Without forceRefresh, an existing canonical result is reused when available') and documents execution constraints like synchronous execution and forbidden task support.

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