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

The description discloses all key behaviors: fan-out to multiple sources (SEC, GDELT/GNews, USPTO), fallback logic (GDELT preferred, GNews on rate-limit/5xx), USPTO soft-fail status, return structure, and citation URIs. This adds significant context beyond the annotations, which already mark it as read-only, idempotent, and open-world.

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 well-structured: front-loaded with examples, followed by detailed source explanations, parameter guidance, and an alternative tool mention. While slightly long (~100 words), every sentence is informative and earns its place. No wasted words, so a 4 is appropriate.

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 the tool's complexity (multiple data sources, fallback, parameter flexibility), the description covers all aspects comprehensively. It explains the return format (structured changes[] grouped by source + total_changes + citation URIs), parameter details, and even caveats (USPTO sunset). No output schema exists, but the description sufficiently conveys what the agent can expect.

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 100% schema coverage, the baseline is 3. The description adds value by explaining the 'since' parameter's accepted formats (ISO date or relative shorthand like '30d', '1y'), recommending '30d' or '1m' for typical monitoring, and clarifying that 'type' only supports 'company' today. This extra context justifies a 4.

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 the tool's purpose: 'change feed for a company in the last N days/weeks/months in ONE parallel call.' It provides concrete usage examples like 'What's new with X' and explicitly distinguishes itself from the sibling tool 'entity_profile' for static profiles.

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 (dynamic changes/updates) and when to use an alternative ('Use entity_profile instead when you want the static profile'). It also includes example queries to help the agent understand the intended use cases.

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