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

Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint), the description discloses data quirks: 'RAUM double counts affiliates', 'no advisor book size exists or is estimated', 'the IAPD tape is survivor-biased before 2026-09-15', and 'Nothing here is predictive'. It also explains the fact class taxonomy (reported, fact_from_registration, derived), which is valuable behavioral context. 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 but every sentence adds value: it covers purpose, input identifiers, filters, output format, data caveats, and exclusions. It is front-loaded with the main resources and output, then elaborates. No fluff or repetition.

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 complexity (16 params, 3 entity types, multiple data sources), the description is remarkably complete. It covers the search input semantics, filtering capabilities, output format, data quality caveats, and alternative tools. The lack of an output schema is mitigated by the explicit 'compact cards' mention and fact class explanation. Pagination is hinted via cursor in the schema, and the description's scope is sufficient for an agent to call 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?

With only 50% schema coverage, the description compensates thoroughly. It explains what `query` accepts (name, firm CRD, SEC file number, individual CRD, private fund id) and the entity_type dependency. It clarifies firm_class as 'the RIA lane's printed classification' and details how filters apply to different entity types (firms by state/class/RAUM, advisors by firm CRD/state, funds by firm CRD/type). This adds meaning beyond the bare schema.

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 states the exact resources (RIA firms, advisors, private funds) and the output format (compact cards with dfx:ria: ids). It explicitly distinguishes from siblings by naming search_pe_firms and search_vc_firms as not applicable and pointing to get_entity for cross-graph entities. This is a clear, specific verb+resource statement.

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 routing guidance: it says 'Not for private equity or venture managers as investors (search_pe_firms, search_vc_firms)' and notes that the same adviser may appear on both graphs via get_entity same_as. It also clarifies what the tool is for (searching RIAs, advisors, funds) and what it is not for (predictive purposes). This gives clear when-to-use vs. when-not-to-use context.

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