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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: results are newest-first, grouped by filing, sourced from EDGAR full-text search, and the return fields are enumerated. It stops short of documenting pagination or truncation behavior across the limit boundary.

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?

A single dense paragraph, but the core purpose and scope lead and every clause carries information (exhibit taxonomy, source, ordering, return fields, handoff). The example-question list is somewhat lengthy, though it doubles as usage guidance rather than filler.

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, but the description enumerates the returned fields (exhibit type, filer description, root form, filing date, document URL, accession) and the grouping, so an agent can interpret results. With 100% parameter coverage and full annotations, nothing needed to call or read the tool is missing.

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 100%, so the schema already documents all six parameters, setting the baseline at 3. The description adds genuine value on top: it expands what each exhibit family means (credit agreements, indentures, M&A) and confirms the company parameter accepts three identifier formats, matching the schema but making the intent legible without opening it.

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 a specific verb and resource (list ONE company's material contracts) plus precise scope: which exhibit families (10/4/2), which filings (8-K/10-K/10-Q/S-1/S-4), and ordering (newest first). The word 'ONE' distinguishes it from the sibling sec_contracts_search, and the closing pointer distinguishes it from sec_contract_text.

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?

Explicitly scopes to a single company and gives the accepted identifier forms (ticker, name, CIK). It names the natural follow-up alternative ('Read any row with sec_contract_text') and frames the use case with concrete example questions, so an agent knows both when to call it and where to go next.

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