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

Annotations already declare readOnlyHint=true, openWorldHint=true, and idempotentHint=true, but the description adds substantial context beyond these: fans out to SEC EDGAR, GDELT→GNews fallback, USPTO soft-fail due to PatentsView API sunset, and returns structured changes grouped by source with citation URIs. It also mentions 'ONE parallel call' and the exact failure mode for GNews, which is valuable operational knowledge.

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 efficient, packing multiple pieces of essential information into one paragraph. It opens with user-intent phrases to aid pattern matching, then covers sources, parameters, output, and the alternative tool. No filler or redundant content is present, though the length may be slightly high for a simple tool; it earns a 4 rather than 5.

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 data sources, fallbacks, date parsing, no output schema), and the description covers all necessary operational details: source list, fallback conditions, date format support, return structure (changes[], total_changes, citation URIs), and limitations (USPTO soft-fail). This is sufficient for an agent to select and invoke the tool correctly without guessing.

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?

Although schema covers all three parameters, the description enriches them: 'since' accepts ISO or relative shorthand with examples ('7d', '30d', '3m', '1y'), 'value' accepts ticker or zero-padded CIK with concrete examples, and 'type' only supports 'company'. This exceeds the schema by providing format examples and recommended usage, reducing ambiguity for the agent.

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?

Description uses specific verbs: 'change feed for a company in the last N days/weeks/months' and provides concrete user intents ('What's new with X', 'updates on Acme'). It explicitly distinguishes from sibling entity_profile by stating when to use that instead, so it is not confused with similar tools.

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?

Description gives clear when-to-use criteria via example queries and typical monitoring window ('Use "30d" or "1m" for typical monitoring'). It also names the alternative tool (entity_profile) and states when it is preferred ('when you want the static profile regardless of window'). Fallback behavior for data sources is described, helping the agent decide when this tool is appropriate.

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