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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is clear. The description adds critical behavioral context: it explains what is NOT included (funds, people, transactions, scores with components) and clarifies that reported gross assets are NOT fund size or dry powder, preventing misinterpretation. It also mentions the classifier's state and confidence, which is useful behavioral nuance. 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 a single dense paragraph that is front-loaded with the key information (what the cards contain) and then covers filtering and exclusions. It is comprehensive but not overly long; the structure could be improved with separators, but the content is necessary and efficient. A 4 is warranted because it says a lot without redundancy.

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?

Given the tool's complexity (9 parameters, many enums) and no output schema, the description is fairly complete: it explains the card contents, the filter options, the meaning of size bands and class states, and directs to get_pe_firm for deeper data. However, a few details are absent: it doesn't explain the 'basis' for size band, the confidence details of the classifier, or the exact format of the return (e.g., pagination via cursor). But the description handles the most critical usage scenarios. A 4 is fair.

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?

The schema description coverage is 89%, which is high, so the schema already documents most parameters. The description does not add much beyond the schema, but it does clarify the meaning of size_band (UNSIZED means no evidence, not 'small') and that class CANDIDATE_PE is not yet ruled on. Since coverage is high, a baseline of 3 is appropriate; the description adds marginal value but does not duplicate the schema extensively.

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 it searches private equity firms and returns compact cards with specific fields. It explicitly distinguishes from get_pe_firm (for funds, people, transactions) and names alternative tools for family offices, independent sponsors, and venture firms. The verb 'Search' plus the resource 'private equity firms' is specific and differentiates it from sibling search tools.

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 provides explicit when-to-use guidance: it is for private equity firms (management companies and advisers), not for family offices, independent sponsors, or venture firms, for which it names alternative tools. It also clarifies the scope of returns (cards, not funds/people/transactions) and directs to get_pe_firm for deeper data. This is exemplary usage guidance.

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