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

Annotations already declare readOnly, idempotent, and non-destructive hints, and the description goes far beyond by disclosing multi-source fan-out (SEC, GDELT, GNews, USPTO), fallback logic, rate-limit handling ('GNews when rate-limited or 5xx'), and the PatentsView sunset causing soft-fail. It also describes the output structure (changes[], total_changes, citation URIs) without contradicting 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 long but each sentence earns its place, covering user triggers, sources, fallbacks, parameter formats, output summary, and alternative tool. It's front-loaded with query examples and flows logically from purpose to mechanics to differentiation. Slightly verbose, but efficient for the tool's complexity.

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?

For a multi-source tool with fallbacks and no output schema, the description provides complete context: purpose examples, source breakdown, fallback logic, parameter semantics, output summary, and an explicit pointer to a sibling tool. Nothing essential is missing, making it highly complete for an agent 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?

The input schema already covers 100% of parameters, so the baseline is 3. The description adds meaningful value by clarifying the 'since' parameter with relative shorthand examples and a recommended default ('Use "30d" or "1m" for typical monitoring'), and by explaining that 'value' can be a ticker or zero-padded CIK with an example. This goes beyond the schema's 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 explicitly states the tool is a 'change feed for a company in the last N days/weeks/months' and provides natural-language triggers like "What's new with X" and "updates on Acme." It also distinguishes itself from the sibling entity_profile tool by telling the agent to use entity_profile for static profile queries, making the purpose and differentiation crystal clear.

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 gives specific when-to-use guidance with example queries and explicitly states when to use an alternative ('Use entity_profile instead when you want the static profile'). It also details fallback behavior (GDELT→GNews, USPTO soft-fail) and source-specific caveats, providing thorough usage context beyond what annotations offer.

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