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

The description discloses key behavioral traits beyond the annotations: it fans out to multiple sources in parallel, describes the fallback mechanism (GDELT preferred, GNews when rate-limited or 5xx), notes a soft-fail for USPTO (PatentsView API sunset), and specifies the return format (structured changes[], count, citation URIs). This provides a clear mental model of the tool's operation.

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 paragraph that efficiently conveys purpose, sources, parameter details, return format, and alternative tool. Every sentence contributes value; there is no redundancy or filler. The structure front-loads common queries and then provides technical details, making it easy to scan.

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?

Despite lacking an output schema, the description sufficiently describes the return structure. Given the tool's moderate complexity (three sources, fallback, parallel calls), the description covers all essential aspects: what it does, how to parameterize it, what happens under failure conditions, and how to interpret results. The mention of an alternative tool closes the completeness gap.

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 the schema already provides descriptions for all parameters (100% coverage), the description enriches them with concrete examples and usage details. For 'since', it illustrates both ISO date and relative shorthand formats with examples. For 'value', it clarifies it accepts tickers or zero-padded CIKs. This adds meaningful context beyond the raw schema.

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 begins with multiple concrete example queries ('What's new with X', 'latest on Y'), immediately clarifying the tool's purpose as a change feed for a company. It specifies the resource (company) and the data sources (SEC EDGAR, GDELT→GNews, USPTO), and distinguishes itself from the sibling tool 'entity_profile' by contrasting the dynamic feed with 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 explicitly states when to use this tool ('What's new with X' scenarios) and when to use an alternative ('Use entity_profile instead when you want the static profile'). It also provides usage hints for the 'since' parameter ('Use "30d" or "1m" for typical monitoring'), guiding appropriate invocation.

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