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 covered. The description adds substantial behavioral context: the entitlement/lock behavior of the free tier (first 5 rows, locked.count, locked.by_type), suppression of contact values and decision-maker names, the `entitlement` and `locked` fields in responses, and a clarification of adv_gross_asset_value semantics. This goes well beyond annotations, though it's interleaved with promotional content.

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 useful enumeration of return fields but then contains a lengthy run-on covering entitlement logic and a promotional URL ('7 days free at https://dfxintel.com/data-factory/plans'). The promotional sentence does not earn its place in a tool definition, and the entitlement paragraph, while relevant, is verbose.

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?

There is no output schema, so the description must carry return-value information — it does list the amount fields returned, which helps. However, it doesn't describe pagination behavior (cursor, limit max 25) or the structure of `locked`, and the promotional content dilutes the technical completeness. Adequate but with clear gaps for a 10-parameter tool.

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 60%, so some parameters rely on the description. The description mentions the filter axes (name, manager, ADV fund type, vintage range, lifecycle, min gross assets) which maps to several params, and clarifies that adv_gross_asset_value is reported gross assets, not fund size — matching the schema's own description of min_adv_gav_usd. No new syntax or format detail is added for parameters like cursor or sort, so baseline 3 is appropriate.

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 the resource (private equity funds) and enumerates the amounts returned (target, first close, final close, announced size, Form D offering/sold, Form ADV GAV) plus vintage, ADV fund type, lifecycle, owner and LP counts. This is a specific verb-less but clearly scoped search, distinct from siblings like search_pe_firms or get_pe_fund. It doesn't explicitly contrast with those siblings, keeping it at 4.

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?

Filter conditions are listed ('Filter by name, manager, ADV fund type, vintage range, lifecycle or minimum reported gross assets'), which implies when this tool is appropriate, but there is no explicit guidance on when to prefer get_pe_fund (single fund lookup) or search_pe_firms, nor exclusions. Usage is implied rather than stated.

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