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

Beyond the annotations (readOnly, idempotent), the description discloses the multi-source fan-out, fallback logic (GDELT preferred, GNews on rate-limit/5xx), USPTO API sunset causing soft-fail, and the output structure. This is valuable operational context that annotations don't cover.

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-structured, starting with example queries, then functionality, source details, fallback, return structure, and an alternative. Every sentence adds value, though the opening quoted examples are slightly redundant with the functional statement.

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 data sources, fallbacks, time windows), the description is comprehensive. It explicitly describes the return shape (changes[], total_changes, citation URIs), fallback behavior, API sunset limitation, and references the key alternative tool. No output schema exists, so this description carries the full burden and succeeds.

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 input schema already covers all three parameters with rich descriptions (e.g., `since` includes ISO/relative examples and recommended values). The description adds little beyond the schema—it restates ticker/CIK and confirms only 'company' is supported, but doesn't introduce new parameter 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 clearly identifies the tool as a change feed for companies over a time window, with concrete example queries ('What's new with X', 'latest on Y'). It specifies the resource (company changes) and distinguishes from sibling entity_profile by explicitly directing users there for static profiles.

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?

It provides explicit usage guidance: example queries, intended use cases, and explicitly says 'Use entity_profile instead when you want the static profile... regardless of window.' It also explains fallback behavior between GDELT and GNews, offering clear when-to-use context.

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