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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds significant behavioral context: it explains the fan-out to SEC EDGAR, GDELT→GNews fallback (GDELT preferred, GNews on rate-limit/5xx), and the USPTO PatentsView API sunset soft-fail. It also discloses the return structure (changes[], total_changes, citation URIs), which goes well beyond the 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 longer than the minimal example but each sentence serves a distinct purpose: intent examples, core definition, source fan-out details, `since` format, return shape, and alternative tool. It is front-loaded with the core purpose and organized logically, though the density makes it slightly less immediate than a two-sentence description.

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?

With no output schema, the description sufficiently explains return values (structured changes[], total_changes, citation URIs). It covers operational caveats like GDELT→GNews fallback and the PatentsView sunset soft-fail, and provides the alternative tool for static needs. For a multi-source aggregation tool, this is complete and actionable.

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 description coverage is 100%, so the baseline is 3. The description adds extra semantics for `since` (relative shorthand examples like '7d', '30d', '3m', '1y', and typical usage guidance) and clarifies `value` as ticker or zero-padded CIK, reinforcing the schema. However, the schema already describes each parameter meaningfully, so the description provides marginal but useful enhancement.

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 clearly identifies the tool as a change feed for a company, starting with real-world example queries ('What's new with X', 'latest on Y') and then defining it as 'change feed for a company in the last N days/weeks/months in ONE parallel call'. It also distinguishes from the sibling tool entity_profile by explicitly stating when to use that instead, satisfying the sibling differentiation criterion.

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 explicit usage guidance: it names the alternative tool (`entity_profile`) for static profiles, specifies the temporal scope ('in the last N days/weeks/months'), and details the `since` parameter formats with a typical recommendation ('Use "30d" or "1m" for typical monitoring'). This constitutes explicit when-to-use and when-not-to-use guidance beyond generic context.

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