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

Beyond the annotations (read-only, idempotent), the description discloses rich behavioral details: parallel fan-out to multiple sources, fallback logic (GDELT preferred, GNews on rate limiting/5xx), the PatentsView API sunset causing soft-fail, and the exact return format (changes[] grouped by source, total_changes, citation URIs). This is substantial added context beyond the safe-read signals.

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 every sentence earns its place. The opening list of natural-language paraphrases is slightly verbose but useful for intent matching. The overall structure flows from purpose to sources to parameters to return shape to alternatives, 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?

Given the tool's complexity (multiple sources, fallback, soft-fail, no output schema), the description is exceptionally complete. It explains the return shape (changes[] grouped by source, total_changes, citation URIs), the window parameter, and the operational caveats (USPTO sunset, rate-limiting fallback), leaving no significant gaps for an agent to invoke it 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?

While the schema already documents all three parameters (100% coverage), the description adds practical nuance: `since` accepts ISO date or relative shorthand with examples ('7d', '30d', '3m', '1y'), recommends '30d' or '1m' for monitoring, and clarifies that `value` can be a ticker or zero-padded CIK. This goes slightly beyond the schema's own 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 defines the tool as a change feed for a company over a time window, listing the specific data sources (SEC EDGAR, GDELT/GNews, USPTO) and the return structure. It also distinguishes itself from sibling tools like entity_profile by explicitly 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 provides explicit usage context with natural language query examples and directs users to an alternative tool ('Use entity_profile instead... when you want the static profile'). It also discloses fallback behavior and limitations (GDELT to GNews fallback, USPTO soft-fail), giving clear guidance on when and how to use the tool.

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