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

Annotations already cover readOnlyHint=true and idempotentHint=true, so the safety profile is established. The description adds genuine behavioral context beyond that: results are de-duplicated by CIK (one record per fund filer), specific form types are queried, the underlying source is the SEC EDGAR full-text API, and no API key is required. No pagination or rate-limit behavior is disclosed, but the added context is meaningful.

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 its main function and organized into labeled sections (PRIMARY USE, examples, de-dup, date filtering, source/authentication). The four example queries add length but demonstrate realistic usage patterns that help an agent form queries correctly. Nothing is redundant; every block carries information, though it runs slightly long.

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 the primary fee-comparison workflow, the description is complete: search semantics, query examples, downstream chaining, de-duplication behavior, date-filtering support, and authentication status are all covered. Minor gaps remain — no pagination/rate-limit guidance and no mention that max_results can be increased for broader scans — but the output schema and annotations cover the rest.

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 reported at 0%, the description must compensate, and it partially does: example queries map keywords and fund_type values, and a line covers date filtering for start/end dates. However, core params like max_results, plus wholesaler_ids, source_resource_id, and others, get no mention in the description, leaving a coverage gap for non-obvious 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 first sentence names a specific verb ('Search'), resource ('SEC EDGAR'), target ('mutual fund and ETF filers'), and selection dimension ('by investment category or keyword'), and states the return fields (entity name, CIK, form type, filing date). The form-type scope (N-1A, 485BPOS, N-2) plus the stated downstream link to GetFundFees clearly differentiates it from siblings like SearchEdgar13F and GetEdgarCompanyFilings.

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?

'PRIMARY USE: Step 1 of fee comparison. Feed the returned CIKs directly into GetFundFees' is an explicit workflow position with concrete downstream chaining, and the four example queries show realistic keyword/fund_type usage. It does not explicitly name alternative tools to prefer in other scenarios, so exclusions from siblings like SearchFredSeries or SearchEdgar13F are left implicit.

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