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

Beyond the readOnlyHint annotation, the description reveals the exact semantics of the two counts, the cross-catalog synthesis nature, and the B2 pricing tier. It even explains how profiled_count maps to find_company_insights(industry:), giving the agent a clear behavioral model. No contradiction with annotations.

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 dense but front-loaded with the core concept ('demand-side industry rollup') and then explains counts, relationship, and pricing in a logical order. It's longer than average but every sentence carries meaningful decision-relevant information; the only minor inefficiency is the 'UNDERSTANDING —' prefix.

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 read-only, paginated list tool with 3 optional params and no output schema, the description covers what the rows mean, which count to use for cohort sizing, how it differs from the sibling find_industries, and pricing. There's no critical missing information for an agent to invoke it 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?

Schema coverage is only 33% (only the context parameter has a description). The tool description doesn't add anything about page or limit semantics, so those two parameters rely entirely on their type/default/min/max constraints. The description does enrich the meaning indirectly by clarifying that rows contain industry and two counts, but not the pagination parameters specifically.

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 defines the tool as a demand-side industry rollup with specific counts, and explicitly distinguishes it from find_industries' supply-side purpose. It names the resource (sectors/industries) and explains the aggregation, so an agent can tell it apart from siblings without opening schemas.

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?

It explicitly states when to use this tool vs find_industries ('counterpart', comparing supply vs demand to find buyers with no sellers) and directs the user to size cohorts on profiled_count. Pricing context is also provided, which helps decide if the call is appropriate.

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