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

Despite annotations already declaring readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, the description adds substantial behavioral context: it explains the fan-out to multiple APIs with fallback (GDELT preferred, GNews when rate-limited or 5xx), the soft-fail for USPTO due to API sunset, the return structure (changes grouped by source, total_changes count, citation URIs), and the `since` format acceptance. 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 long but efficiently packed: it begins with relatable user queries, then concisely describes the mechanism, sources, parameter details, and alternatives in a logical flow. Every sentence adds necessary information, and no wasted words are present.

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 tool's complexity (multiple sources, no output schema, rate-limit behavior, API sunset), the description is remarkably complete. It covers return format, fallback logic, soft-fail scenarios, parameter formats, and provides a clear alternative. There are no gaps in contextual information needed for an agent to use the tool 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% (all three parameters described in schema), yet the description adds value beyond: for `since`, it provides examples ('2026-04-01', '7d', '30d', '3m', '1y') and a usage suggestion ('30d or 1m for typical monitoring'). For `value`, it clarifies that both ticker and CIK are accepted. For `type`, it notes only 'company' is supported. This enriches the schema information.

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 starts with explicit user query examples ('What's new with X', 'latest on Y'), clearly defining the tool as a change feed aggregator. It specifies the three data sources (SEC EDGAR, GDELT/GNews, USPTO) and distinguishes itself from the sibling tool `entity_profile` by contrasting dynamic vs. static profiles. This makes the purpose specific, actionable, and differentiated.

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 explicitly states when to use the tool ('change feed for a company in the last N days/weeks/months') and when not to, by directing the agent to `entity_profile` for static profiles. It also covers the `since` parameter with recommendations like 'Use 30d or 1m for typical monitoring.' This provides clear usage context and alternatives.

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