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

Annotations already declare safe, non-destructive, idempotent behavior. The description adds value by detailing the multi-source fan-out, fallback mechanism, and output structure (changes[] grouped by source + total_changes + citation URIs). No contradiction with annotations.

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?

Single paragraph, front-loaded with user-facing query examples. Every sentence adds essential information. No redundancy or fluff.

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?

Despite no output schema, the description explains return fields and grouped structure. It covers all 3 required parameters thoroughly, including fallback behavior and limitations (USPTO soft-fail). Complete for the tool's complexity.

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%, and the description enriches each parameter: 'type' is limited to 'company', 'since' accepts ISO or relative shorthand with examples, 'value' can be ticker or CIK. It adds practical tips beyond schema.

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 clearly states it provides a change feed for a company, listing example queries like 'What's new with X' and specifying the data sources (SEC EDGAR, GDELT→GNews, USPTO). It directly distinguishes from the sibling tool 'entity_profile', so the agent can differentiate.

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?

Explicit guidance is given: when to use (recent changes) and when not (use entity_profile for static profile). It explains fallback behavior (GDELT→GNews) and provides recommendations for the 'since' parameter ('Use "30d" or "1m" for typical monitoring').

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