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

Although annotations already declare readOnly, openWorld, idempotent, non-destructive, the description adds valuable behavioral detail: it fans out to multiple APIs in parallel, handles rate-limit fallbacks, soft-fails for patents, and returns structured changes[] grouped by source plus citation URIs. It also specifies `since` accepts ISO dates or relative shorthand with examples, which is beyond the 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 dense but every sentence serves a purpose: query patterns, core function, data sources with fallback, parameter formats, output structure, and sibling-tool pointer. It is front-loaded with the most useful information and remains readable despite its length. No fluff.

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?

The tool is complex (multiple external APIs, fallbacks, soft-fails, date parsing) but the description covers all essential aspects: inputs, outputs, limitations, and alternatives. Since there is no output schema, it describes the return structure (changes[] grouped by source, total_changes, citation URIs). This is a complete and self-contained description.

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% and already provides descriptions, but the description enriches meaning further: it explains `since` with both ISO and relative examples ("7d", "30d", "3m", "1y") and recommends "30d" or "1m" for typical monitoring. It clarifies `value` accepts tickers or zero-padded CIK with concrete examples. This goes well beyond the 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 clearly states the tool's purpose: "change feed for a company in the last N days/weeks/months" with specific sources (SEC EDGAR, GDELT/GNews, USPTO). It uses a specific verb+resource+scope and immediately differentiates from sibling entity_profile by noting when to use that instead.

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 opens with natural-language query examples ("What's new with X", "what happened to Z this week") to signal when it's appropriate. It explicitly says "Use entity_profile instead when you want the static profile", providing an exclusion criterion. It also explains fallback logic (GDELT preferred, GNews on rate-limit/5xx) to manage expectations.

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