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

Annotations already mark it read-only and idempotent, but the description adds substantial behavioral detail: fan-out to SEC EDGAR, GDELT→GNews fallback logic (GDELT preferred, GNews on rate-limit/5xx), USPTO soft-fail due to PatentsView API sunset, and return structure (changes[] grouped by source + total_changes + citation URIs). No contradiction 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 dense but purposeful. Every sentence adds value: example intents aid pattern-matching, then the core functionality, data sources, fallback behavior, date format, output structure, and alternative tool. The structure is logical and front-loaded with the most important use-case info, and while long, it earns its length.

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 detailing the return shape (changes[] grouped by source, total_changes count, pipeworx:// URIs). It also covers input formats, data source behaviors, and an explicit alternative for static profiles. An agent has enough context to select and invoke this tool correctly without additional documentation.

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 covers all 3 parameters, but the description enriches them significantly: explains `since` accepts ISO or relative shorthand with examples ('7d','30d','3m','1y') and recommends '30d' or '1m' for monitoring; clarifies `value` as ticker or zero-padded CIK; notes `type` only supports 'company'. This goes 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 opens with natural-language intents ('What's new with X', 'latest on Y') then defines the tool as a 'change feed for a company in the last N days/weeks/months in ONE parallel call.' It specifies the resource (company change feed) and the action (get changes), and explicitly distinguishes from entity_profile, naming it as the alternative for static profiles. This clearly differentiates from siblings.

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 usage context through example queries and states when to use the tool. It also gives a clear exclusion: 'Use entity_profile instead when you want the static profile (filings + fundamentals + LEI + patents) regardless of window.' The 'ONE parallel call' phrasing signals that this tool replaces separate calls to SEC/GDELT/USPTO, giving practical guidance on when to invoke it.

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