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

Annotations already mark the tool as read-only and idempotent. The description adds valuable behavioral context: it fans out to multiple sources with specific fallback logic (GDELT preferred, GNews when rate-limited), mentions API limitations (USPTO sunset soft-fail), and describes output structure. No contradictions with 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 moderately long but well-organized. It begins with clear usage examples, then explains source behavior, parameter details, and output format. Every sentence contributes useful information, though a minor reduction in verbosity could be justified.

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?

Given the tool's complexity (multiple data sources, fallback mechanisms, and no output schema), the description covers essential aspects: input formats, source behavior, output structure (changes[], total_changes, citation URIs), and cross-reference to sibling tool. It lacks details on pagination or rate limits but is otherwise comprehensive.

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%, so baseline is 3. The description significantly enhances parameter meaning: explains 'since' accepts ISO dates or relative shorthand (e.g., '30d'), recommends a default ('30d' or '1m'), and clarifies 'value' can be ticker or CIK. This adds crucial nuance beyond the schema's simple 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 provides a change feed for companies, listing example queries and detailing the sources (SEC, GDELT/GNews, USPTO). It distinguishes from the sibling entity_profile by specifying this is for dynamic changes rather than 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?

The description provides explicit guidance: use for 'what's new' queries and recommends entity_profile for static profiles. It also gives parameter examples and explains fallback behavior, helping the agent decide when to invoke this tool.

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