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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds non-obvious behavioral context on top: results are 'de-duplicated by CIK (one record per fund filer)', 'No API key required', and the data source is 'SEC EDGAR full-text search API'. These are traits an agent cannot infer from annotations or the tool name, and there is no contradiction with the read-only hints.

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 well-structured and front-loaded: a purpose sentence, a bolded PRIMARY USE callout, a compact indented example block, then behavior notes and source attribution. It is longer than the minimal two-sentence style, but the length is justified by the domain complexity and the 12-parameter surface; each section earns its place with minimal 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?

For a tool that has an output schema and rich annotations, the description covers everything needed for selection and correct invocation: purpose, workflow position, return fields, de-duplication behavior, date filtering, source, and authentication requirements. Minor gaps keep it from a 5 — the params wrapper object is implied rather than stated, and max_results sizing guidance lives only in the nested schema rather than in the description.

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 schema_description_coverage at 0% at the top level, the description must compensate, and it does partially: the example block teaches the two most important parameters with concrete value→outcome mappings ('keywords='commodity', fund_type='etf'' → 'commodity ETF universe'), and it mentions date filtering. However, start_date/end_date syntax, max_results behavior, and the internal parameters (wholesaler_ids, source_resource_id, mcp_prompt_id) are left entirely to the nested $defs descriptions, which carry most of the semantic load.

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 leads with a specific verb+resource scope: 'Search SEC EDGAR for mutual fund and ETF filers by investment category or keyword', names the exact filing forms queried (N-1A, 485BPOS, N-2), and states the return fields (entity name, CIK, form type, filing date). It also positions the tool within a workflow relative to sibling tools like GetFundFees, so an agent can distinguish it from the other search siblings without opening schemas.

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 'PRIMARY USE' section explicitly says when to invoke this tool — 'Step 1 of fee comparison' — and names the downstream step: 'Feed the returned CIKs directly into GetFundFees to retrieve expense ratios'. This is clear workflow guidance with a named sibling. It stops short of explicit exclusions (e.g., use LookupTicker for a known symbol, or go straight to GetFundFees when CIKs are already in hand), which keeps it at a 4 rather than a 5.

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