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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safe-read profile is known. The description adds substantial behavioral context beyond those annotations: feeder assets are counted twice, GAV is never fund size/commitments/dry powder, a quarantined reading enters no sum, the tape only spans 2011-2024 so first reports are first sightings, and holdings appear only where binding passed blind labels. This rich caveat set fully discloses the tool's interpretation quirks.

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 long but every sentence earns its place: each caveat (feeder exclusion, GAV definition, date range, quarantine, blind labels) prevents a likely misinterpretation. It is front-loaded with the core enumeration and then layered with necessary caveats. No fluff or repetition, though it could be slightly tightened with bullet points without losing content.

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 complex 15-parameter search tool with no output schema, the description covers a large share of the contextual burden: output fields, query formats, data vintage, feeder policy, GAV interpretation, and the limits of holdings data. Missing context includes pagination behavior (though cursor is self-described in schema) and explicit semantics for several sort/filter parameters, which prevents a perfect score.

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 description coverage is only 40%, so the description carries extra responsibility. It adds meaning for 'query' (already in schema) and clarifies the 'exclude_feeders' default and the GAV semantics that underlie 'min_gav_usd'. Yet many parameters—sort's enum values, limit, manager_crd, vehicle_kind, vintage_year, with_public_lps, first_reported_year—receive no added explanation beyond their raw type/enum, leaving a notable gap in a tool with 15 parameters.

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 opens with a specific verb ('Search') and resource ('real estate fund vehicles'), then enumerates the exact attributes returned (fund family, GAV, vintage, owners, Form D, lifecycle state, public plans). It also specifies the query formats (name, 805- id, 021- Form D), making the tool's scope unmistakable and clearly distinct from siblings like get_re_fund_vehicle or search_re_fund_managers.

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 operational guidance such as 'Feeders are excluded unless asked for' and clarifications about GAV semantics, which help the agent decide how to filter and interpret results. However, it never explicitly names alternatives like get_re_fund_vehicle for a single known vehicle or search_re_fund_managers for manager-focused queries, leaving the when-to-use-vs-sibling decision implicit.

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