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

Annotations indicate read-only, idempotent, and non-destructive behavior. The description adds substantial context: it fans out to three sources, includes fallback logic for GDELT→GNews, soft-fail for USPTO, and explains the return structure (changes grouped by source, total_changes, citation URIs). No contradiction 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 concise, front-loaded with concrete example queries, and every sentence contributes meaning. It efficiently covers multi-source behavior, parameter format, fallback, and output summary without excess.

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 (multi-source, fallback, soft-fail, no output schema), the description is complete. It explains return structure (changes grouped, total_changes, citation URIs), source behavior, and the date format. The agent has enough context to select and invoke the tool correctly.

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 good parameter descriptions. The description adds value by clarifying acceptable inputs (e.g., 'type' only 'company', 'value' examples like 'AAPL' or '0000320193') and recommending '30d' or '1m' for typical monitoring. This goes beyond the schema's basic types.

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 states the tool's purpose: returns a change feed for a company from multiple sources (SEC EDGAR, GDELT/GNews, USPTO) in a single call. It explicitly distinguishes from the sibling tool 'entity_profile', which provides a static profile. The verb 'recent_changes' combined with the examples exactly captures the tool's scope.

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: for queries like 'what's new' or 'latest updates'. It directly advises using 'entity_profile' instead for static profiles. The fallback logic (GDELT preferred, GNews on rate-limit/5xx) is also explained, helping the agent decide invocation.

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