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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and no destructive hint. The description adds critical behavioral context: parallel fan-out to three sources, fallback from GDELT to GNews on rate limits/5xx, soft-fail for USPTO due to API sunset, and the return structure (changes grouped by source, total_changes count, pipeworx citation URIs). 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 comprehensive and well-structured, using bullet-like sections within a single paragraph. It is slightly dense due to the amount of context packed in, but every sentence adds value. A minor reorganization could improve readability, but it remains efficient given 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?

Given three parameters, no output schema, and high schema coverage, the description fully covers the purpose, usage, data sources, behavior, and return structure. It explicitly mentions the return format (changes[] grouped by source, total_changes, citation URIs), compensating for the lack of an output schema. The alternative tool is clearly described, making the context complete for an AI agent.

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 significant value: examples for each parameter (ticker 'AAPL', CIK '0000320193'), clarification of 'since' format (ISO date vs relative shorthand like '7d', '30d', '3m', '1y'), and a recommendation for typical monitoring windows. The enum for 'type' is already clear, but the description reinforces the current limitation.

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 begins with example queries ('What's new with X', etc.) and clearly states it is a change feed for a company over a recent window. It specifies the aggregated sources (SEC EDGAR, GDELT→GNews, USPTO) and distinguishes itself from the sibling tool 'entity_profile', which covers static profiles regardless of time window.

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?

Explicitly tells when to use this tool versus alternatives: 'Use entity_profile instead when you want the static profile (filings + fundamentals + LEI + patents) regardless of window.' It also provides clear context for typical monitoring ('Use "30d" or "1m" for typical monitoring') and describes fallback behavior between GDELT and GNews.

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