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

The description adds significant behavioral context beyond annotations: parallel fan-out to multiple sources, fallback logic, soft-fail for USPTO, and output structure (changes grouped by source, total count, citation URIs). Annotations already indicate read-only, idempotent, non-destructive, and the description aligns with these.

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?

Although somewhat long, every sentence is necessary and informative. The description front-loads the purpose with common queries, provides parameter details, sources, fallback, and output format. No redundancy or wasted words.

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 complexity (multiple data sources, fallback logic, no output schema), the description is complete. It explains the input parameters, output structure, and distinguishes from a sibling tool, enabling the agent to select and invoke 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?

Schema coverage is 100%, but the description adds substantial value: explains `since` parameter with examples of ISO date and relative shorthand, recommends typical use ('30d' or '1m'), and clarifies `value` accepts ticker or CIK. For `type`, it notes only 'company' supported.

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 provides a 'change feed for a company in the last N days/weeks/months' and lists specific sources (SEC EDGAR, GDELT/GNews, USPTO). It distinguishes from sibling tool 'entity_profile' by explicitly stating when to use that alternative.

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 usage examples ('What's new with X', 'latest on Y') and gives guidance on fallback behavior (GDELT→GNews). It also explicitly states when not to use this tool ('Use entity_profile instead when you want the static profile').

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