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

Annotations already cover read-only, idempotent, non-destructive, and closed-world behavior. The description adds useful context beyond those: it explains that provider, account, metric, and publication-age cohort remain distinct in results; that fewer than three comparable peers are marked insufficient; that sourceTruncated signals repository read limits; and that raw metrics are not compared across platforms. This is strong behavioral disclosure, though it does not explain how 'managed and imported history' differ or how metrics are aggregated.

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 description is front-loaded with the core purpose and consists of six tight sentences, each contributing specific behavioral or constraint information. It is efficient and well-structured, though slightly dense in places and could be marginally tighter.

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?

The tool has six parameters, no required fields, and 0% schema description coverage, so the description should ideally document each parameter's meaning. It covers some parameters and explains output indicators like sourceTruncated, but leaves limit and groupName undocumented and does not clarify enum values or day formatting. Given the presence of an output schema, return values need not be explained, but parameter documentation remains incomplete.

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 0% schema description coverage across six parameters, the description must carry the full burden. It mentions time window and scope, and refers to topic/label and idea filters, which partially maps to days, scope, dimension, and ideaId. However, it omits the limit and groupName parameters entirely, does not clarify the meaning of the scope or dimension enums, and gives no format details for days. The description only marginally compensates for the schema gap.

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 clearly states the tool compares topics, labels, and linked ideas across managed and imported history within a time window and scope. This is a specific verb and resource, but it does not explicitly differentiate from sibling tools like get_idea_potential or list_ideas, leaving the agent to infer the distinction.

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 implies usage for performance comparison with optional filters and mentions that insufficient peers are marked, but it does not state when to use this tool over alternatives such as get_idea_potential or list_ideas. No explicit usage boundaries are provided.

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