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

Beyond the annotations (readOnly, openWorld, idempotent, non-destructive), the description discloses important behavior: fan-out to multiple sources, GDELT→GNews fallback on rate limits or 5xx, USPTO soft-fail due to PatentsView sunset, and the structured output shape. This gives the agent a realistic model of how the tool behaves.

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 front-loaded with likely user questions, then delivers a dense but well-organized summary of behavior, fallbacks, outputs, and the alternative tool. Every sentence adds value and there is no fluff; the length is justified by the tool's 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?

With no output schema, the description compensates by explicitly stating the return shape: structured changes[] grouped by source, total_changes count, and citation URIs. It also covers data sources, error/fallback behavior, and the key alternative, making the description complete for an agent to select and invoke the tool.

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 input schema already covers all three parameters with 100% coverage, including format details for `since` and examples for `value` and `type`. The description repeats the `since` format but adds no new parameter-level semantics beyond what the schema provides, so the baseline of 3 is appropriate.

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 defines the tool as a change feed for a company over a recent window, with concrete natural-language examples ('What's new with X', 'updates on Acme'). It distinguishes itself from the sibling entity_profile by explicitly positioning recent_changes as the windowed dynamic feed versus the static profile.

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 explicit guidance on when to use this tool, including the quoted user-intent patterns. It also names the alternative entity_profile and specifies the exact condition under which to use it instead (static profile regardless of window), giving the agent clear decision criteria.

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