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

While annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, the description adds substantial behavioral context beyond these: it fans out to multiple sources in parallel, uses a GDELT→GNews fallback under specific conditions, has a soft-fail for USPTO due to API sunset, and returns structured changes[] grouped by source with citation URIs. This is rich, non-obvious behavior that the annotations alone do not convey.

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 well-organized: query examples first, then core purpose, then data source details, parameter semantics, return format, and an explicit alternative. Every sentence contributes value. The list of examples is front-loaded to help the agent match user intents. It is longer than average but justified by the tool's complexity, and there is no fluff.

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?

This tool has no output schema, but the description compensates by stating the return structure (changes[] grouped by source, total_changes count, pipeworx:// citation URIs). It also covers edge cases (fallback sources, rate limiting, API sunset soft-fail, supported entity type) and provides a clear contrast with entity_profile. For a tool that fans out to multiple external APIs, this is a complete and self-contained description.

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?

The schema already covers all parameters with 100% description coverage, so the baseline is 3. The description goes beyond this by explaining `since` relative shorthand ('7d', '30d', '3m', '1y'), recommending '30d' or '1m' for typical monitoring, clarifying that `value` accepts a ticker or zero-padded CIK, and noting that `type` currently only supports 'company'. This adds meaningful usage nuance beyond the schema.

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 opens with explicit query examples ('What's new with X', 'latest on Y') and then states the core function: 'change feed for a company in the last N days/weeks/months in ONE parallel call.' It clearly identifies the resource (company change feed) and distinguishes from the sibling tool entity_profile by contrasting dynamic change feed vs. static profile.

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 strong usage context via natural language examples and explicitly names an alternative: 'Use entity_profile instead when you want the static profile (filings + fundamentals + LEI + patents) regardless of window.' It also explains fallback behavior (GDELT preferred, GNews when rate-limited or 5xx) and the soft-fail for USPTO, giving the agent concrete guidance on when to expect what.

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