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

Annotations already declare safety (readOnlyHint, idempotentHint, destructiveHint false). Description adds valuable behavioral context: fans out to multiple sources, fallback logic, soft-fail for USPTO, and output format (structured changes[] with citations). No contradiction.

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?

Description is packed with information but end-to-end efficient. Front-loads examples. Every sentence adds value. Could be slightly more structured (e.g., bullet points), but remains concise overall.

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 moderately complex tool (multiple sources, fallback, date parsing), the description is complete. Covers behavior, input formats, fallback logic, output structure, and sibling differentiation. No output schema, but description adequately describes return format.

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%, but description adds semantics: explains `since` accepts ISO or relative shorthand with examples, suggests '30d' or '1m' for typical monitoring, and clarifies `value` can be ticker or zero-padded CIK.

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 clearly states the tool retrieves a change feed (SEC filings, news, patents) for a company in a recent time window, using specific verbs like 'fans out'. It explicitly distinguishes from sibling tool entity_profile (static profile vs. dynamic changes).

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 explicit guidance: when to use (e.g., 'What's new with X') and when not to ('Use entity_profile instead when you want the static profile...'). Also details fallback behavior (GDELT→GNews) and acceptable date formats.

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