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

Despite readOnlyHint/idempotentHint annotations already declaring safety, the description adds behavior beyond them: it discloses fans-out behavior to multiple sources, fallback logic (GDELT→GNews when rate-limited or 5xx), USPTO soft-fail due to PatentsView API sunset, and relative date parsing ('7d', '30d', '3m', '1y'). This is rich behavioral context the annotations don't provide.

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 but well-organized paragraph, front-loads the query patterns in quotes, and every sentence adds information. It avoids restating the title or schema verbatim, and the length is appropriate for the tool's multi-source complexity.

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 zero output schema, the description compensates by explicitly listing return elements: structured changes[], total_changes count, pipeworx:// citation URIs. It also covers source behavior, fallback, and failure modes. The tool is complex (multi-source, two param formats, one enum), and the description addresses all of that with no ambiguity.

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 coverage is 100%, so the baseline is 3. The description adds meaningful semantics beyond the schema: it explains the `since` parameter's supported formats (ISO vs relative shorthand) and gives concrete examples. It also adds domain context for `value` (ticker or CIK) and notes the only supported entity type. Minor deduction because the schema already describes all parameters and the description's added value, while useful, is not exhaustive (e.g., no guidance on valid date ranges).

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 uses a specific verb-resource pair ('change feed for a company') and clearly distinguishes from sibling tools like entity_profile by explicitly contrasting what this tool does versus that static-profile tool. It names the exact data sources (SEC EDGAR, GDELT/GNews, USPTO) and the output shape, so purpose is unmistakable.

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 explicit guidance on when to use this tool: for 'What's new with X' / 'latest on Y' / temporal query patterns over the last N days/weeks/months. It also names an alternative (entity_profile) and states when to use that instead ('when you want the static profile... regardless of window'), satisfying the when/alternative test.

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