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

While annotations already mark this as read-only/idempotent, the description adds substantial behavioral context: it fans out to multiple sources in parallel, uses a fallback chain (GDELT preferred, GNews when rate-limited or 5xx), soft-fails for USPTO due to a known API sunset, and specifies that results include structured changes grouped by source with citation URIs. This greatly exceeds the annotation baseline.

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 compact yet information-dense. It front-loads user-facing query examples, then covers source behavior, date syntax, output structure, and a sibling distinction—all in a single paragraph. Every sentence contributes new information without redundancy.

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?

Despite lacking an output schema, the description clearly states the return shape ('structured changes[] grouped by source + total_changes count + pipeworx:// citation URIs'). It covers fallback logic, known API limitations, and parameter syntax. For a multi-source aggregation tool, this is a complete and actionable specification.

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 covers all three parameters with descriptions, but the tool description adds valuable semantics: 'since' accepts ISO dates or relative shorthand with examples ('7d', '30d', '3m', '1y') and a recommended value ('30d' or '1m'); 'value' gets ticker/CIK examples; and 'type' is noted as only 'company' supported today. This enriches schema meaning.

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 query examples and then states a specific function: 'change feed for a company in the last N days/weeks/months in ONE parallel call.' It enumerates data sources (SEC EDGAR, GDELT→GNews, USPTO) and explicitly differentiates from the sibling tool entity_profile, making the tool's purpose unambiguous.

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 clear when-to-use signals via example phrasings ('What's new with X', 'latest on Y') and gives an explicit alternative: 'Use entity_profile instead when you want the static profile...' It also documents the fallback behavior for news sources, giving the agent guidance on expected data availability.

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