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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, but the description adds substantial behavioral context: fan-out to multiple external APIs, fallback logic (GDELT preferred, GNews on rate-limit/5xx), and a soft-fail for USPTO due to PatentsView sunset. It also discloses the return structure (changes[], total_changes, pipeworx:// URIs), which is beyond what annotations 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 information-dense and well-structured, front-loading with user-intent phrases and then methodically covering sources, parameter format, return structure, and alternative. Though lengthy, every sentence contributes; the length is justified by the tool's multi-source complexity. It avoids redundancy with the schema, making it efficient for its scope.

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?

With no output schema, the description compensates by describing the return format ('structured changes[] grouped by source + total_changes count + pipeworx:// citation URIs'). It covers edge cases like PatentsView sunset and GNews fallback, and clearly delineates when to use entity_profile. For a complex fan-out tool, this is complete and self-sufficient.

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 baseline is 3. The description adds value for `since` by giving explicit formats and examples ('2026-04-01', '7d', '30d', '3m', '1y') and recommending '30d' or '1m' for typical monitoring. It also reinforces that `value` accepts ticker or zero-padded CIK, matching the schema but providing applied context.

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 opens with concrete user-intent phrasing ('What's new with X' / 'updates on Acme') and then states it is a 'change feed for a company in the last N days/weeks/months in ONE parallel call.' It goes on to enumerate specific sources (SEC EDGAR, GDELT→GNews, USPTO), which distinguishes it from sibling entity_profile (static profile). This is a specific verb+resource with clear differentiation.

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 example queries and explicitly names an alternative: 'Use entity_profile instead when you want the static profile... regardless of window.' It also advises on typical usage with 'Use "30d" or "1m" for typical monitoring,' and explains when to expect fallbacks (GDELT→GNews on rate-limit/5xx). This is explicit when-to-use and alternative guidance.

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