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

Beyond the annotations (readOnly, openWorld, idempotent), the description discloses fan-out to multiple sources, fallback behavior, the USPTO API sunset, and the exact return structure. It also clarifies the 'since' parameter format and typical usage, which is not covered by the 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?

The description is dense but every sentence adds critical information: usage examples, source lists, fallback logic, parameter formats, return structure, and alternative tool. No filler or redundancy exists, and the structure flows logically from use case to behavior to parameters to output.

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 fully explains the return structure (changes[] grouped by source, total_changes, citation URIs). It also covers edge cases like the USPTO soft-fail and GNews fallback, making the tool's behavior predictable in complex scenarios.

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?

The schema already covers all parameters with descriptions (100% coverage), so the baseline is 3. The description adds value by providing concrete examples for 'since' ('2026-04-01', '7d', '30d') and a recommendation ('30d' or '1m' for typical monitoring), which goes beyond the schema's generic explanation.

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 identifies the tool as a change feed for a company in a time window, with concrete query examples like 'What's new with X'. It explicitly distinguishes this from entity_profile, which provides static profiles. The verb 'change feed' and resource 'company' are specific and unambiguous.

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 when-to-use guidance via examples and contrasts with entity_profile: 'Use entity_profile instead when you want the static profile'. It also explains the fallback logic (GDELT→GNews) and notes the USPTO soft-failure, setting expectations for when the tool may not return complete data.

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