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

Annotations already declare read-only, openWorldHint=false, idempotent, non-destructive, so the safety profile is covered. The description adds useful behavioral context: scores are 0–100, backed by observations, and it returns dfx:isi: ids. But it omits pagination, result ordering behavior, or score semantics beyond the filter threshold.

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 essentially one dense but well-structured sentence listing what is returned and how to filter. It is appropriately sized and front-loaded with the core signal, though the run-on structure slightly reduces clarity.

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 12 parameters, no output schema, and many undocumented fields in the schema, the description does a good job explaining the core output (scores, observations, ids) and the main filter families. It stops short of describing every parameter, leaving some gaps for the lower-value fields.

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%, so the schema leaves many parameters (city, sort, limit, query, naics_prefix, record_status, max_participants, min_participants) undocumented. The description compensates by grouping filters and naming vertical, state, NAICS prefix, size and minimum opportunity, though it doesn't explain individual undocumented params like sort or city.

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?

States a specific verb (search) and resource (US private companies) and the distinctive signal: an ownership transition evidenced by filings. It clearly distinguishes itself from sibling search tools like search_entities or search_vc_firms because it targets transitioning private companies with scores.

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 gives the domain and filters (vertical, state, NAICS prefix, size, minimum opportunity), implying when to use it. But it never names alternatives or states when not to use this tool (e.g., search_entities for non-transition companies). Usage is implied, not explicit.

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