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

The description discloses significant behavioral traits beyond the annotations: it fans out to multiple source APIs, states the GDELT→GNews fallback on rate limits or 5xx, and notes that USPTO patents soft-fail due to the PatentsView API sunset. It also mentions the parallel execution. This enriches the agent's mental model beyond what readOnly/openWorld/idempotent hints provide, with no contradiction.

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 and thorough but not unnecessarily verbose. It front-loads with user-friendly question paraphrases, then lists the source fan-out, fallback logic, parameter formats, return structure, and an explicit alternative. There is some redundancy (e.g., repeating since formats), but each section earns its place given the tool's complexity.

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?

The description provides a complete picture: the scope (company + time window), the upstream sources and their fallback behavior, the `since` parameter semantics, the return structure (changes[], total_changes, citation URIs), and a clear pointer to entity_profile for static needs. Given there is no output schema, the description fully compensates by specifying what is returned.

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?

Although schema coverage is 100%, the description adds value by clarifying the 'since' parameter with examples ('7d', '30d', '3m', '1y') and a recommendation ('Use "30d" or "1m" for typical monitoring'). It also reiterates ticker or CIK formats for 'value' and confirms 'type' is limited to 'company'. These additions go beyond the bare schema field 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 clearly identifies this as a change feed for a company over a time window, listing example queries and the data sources it covers (SEC EDGAR, GDELT/GNews, USPTO). It explicitly distinguishes itself from entity_profile, so the purpose is specific and well-differentiated 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?

The description explicitly says 'Use entity_profile instead when you want the static profile...' which is a clear alternative and a when-not to use this tool. The query examples and the note about ONE parallel call imply appropriate use cases, though it doesn't discuss alternatives like recent_alerts. This is strong guidance.

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