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

Annotations already cover read-only, open-world, idempotent, and non-destructive hints. The description adds significant behavioral detail beyond that: fans out to SEC EDGAR, GDELT/GNews (with fallback conditions), and USPTO (including the API sunset causing soft-fail). It also discloses the parallel execution and return format, which annotations do not provide.

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-organized: starts with user intent, then states the core action, enumerates sources and fallbacks, explains the key parameter format, describes the return shape, and ends with an explicit alternative. Every sentence adds distinct value; no filler or repetition of schema fields.

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 states the return structure (changes[], total_changes, citation URIs). It covers the multi-source behavior, fallback logic, the `since` format, and parameter semantics. It also provides a pointer to the sibling tool that covers the static-profile use case, making the description self-sufficient for the tool's complexity.

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 useful parameter descriptions, but the description adds extra nuance: it clarifies 'since' accepts ISO dates and relative shorthand with concrete examples ('7d', '30d', '3m', '1y'), and for 'value' gives examples of ticker and zero-padded CIK. This enriches the schema beyond baseline.

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 opens with concrete user intents ('What's new with X', 'latest on Y') and then clearly states the tool's function: a change feed for a company over a window in one parallel call. It explicitly distinguishes this from sibling tool entity_profile by directing users to that tool for static profiles.

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 clear when-to-use signals via example queries ('news on Tesla recently') and explicitly says to use entity_profile instead when a static profile is needed 'regardless of window.' Also describes fallback behavior (GDELT→GNews, USPTO soft-fail) which sets expectations for when and how to rely on results.

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