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

Adds significant behavioral context beyond annotations: fans out to multiple sources (SEC EDGAR, GDELT, GNews, USPTO), explains fallback logic (GDELT preferred, GNews on rate limit/5xx), and notes the PatentsView API sunset causing soft-fail. Also describes the output structure (changes[] grouped by source + total_changes + citation URIs), which the annotations do not cover.

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 well-structured: starts with example queries, then explains the data sources, date format, return shape, and alternative tool. Each sentence carries relevant information for a multi-source API with fallback behaviors, though it is longer than strictly necessary.

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 logic, date parsing, and no output schema), the description covers all critical aspects: what it returns, how sources behave, the 'since' format, and when to use a sibling tool. The lack of an output schema makes the detailed return description essential, and it is provided.

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% with descriptions for all three parameters. The description adds value by explaining the meaning of 'since' with examples and recommending '30d' or '1m' for typical monitoring. It also clarifies that 'value' accepts ticker or CIK, and that 'type' is limited to 'company', reinforcing schema details.

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, with specific verb phrases like 'What's new with X' and 'change feed for a company in the last N days/weeks/months'. It distinguishes itself from the sibling tool entity_profile by explicitly stating 'Use entity_profile instead when you want 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?

Provides explicit usage triggers (e.g., 'latest on Y', 'updates on Acme') and a clear alternative (entity_profile for static profiles). It also documents nuanced behavior like GDELT→GNews fallback and USPTO soft-fail, helping the agent decide when to invoke this tool and what to expect.

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