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

Annotations declare readOnly, openWorld, idempotent, non-destructive. The description adds significant behavioral context: parallel calls to multiple sources, failover logic, soft-fail for USPTO, and structured return format with citation URIs. No contradictions 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?

The description is a single dense paragraph that efficiently conveys purpose, usage, and behavior. Every sentence adds value, though it could be slightly more structured (e.g., bullet points) for easier scanning. Still, it's concise and front-loaded with examples.

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?

For a complex multi-source tool without output schema, the description provides return format details (changes grouped by source, total count, URIs). It covers edge cases like GDELT rate limiting and USPTO sunset. Missing details on pagination or limits, but overall complete enough for effective use.

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?

Although schema coverage is 100%, the description enriches parameter meaning: it explains the since parameter with examples of ISO dates and relative shorthand, suggests typical monitoring usage, and clarifies value accepts ticker or CIK. This adds value beyond the schema's basic descriptions.

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 specifies the tool's purpose: a change feed for a company within a time window, fanning out to multiple sources. It uses concrete examples ('What's new with X') and explicitly distinguishes from the sibling tool entity_profile, which provides static profiles instead of changes.

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 (queries like 'what's new') and when-not-to-use (use entity_profile for static profiles). It also explains the source fan-out behavior with failover (GDELT preferred, GNews fallback) and the soft-fail for USPTO, helping the agent know what to expect.

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