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

The description goes far beyond the annotations by detailing the parallel fan-out architecture, the fallback chain from GDELT to GNews with specific failure conditions, the USPTO soft-failure status, accepted date formats, and the structure of the return value. Annotations already indicate read-only and idempotent behavior, but the description adds rich behavioral context.

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 a single efficient paragraph with no wasted words. Every sentence adds critical information: usage examples, data sources, parameter guidance, return structure, and sibling differentiation. It is as concise as possible given the complexity of the tool.

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 having no output schema, the description fully covers the return format (structured changes grouped by source, total_changes count, citation URIs). It addresses parameter nuances, fallback behavior, and a notable limitation (USPTO soft-fail). It also explicitly differentiates from a sibling tool, making the decision boundary clear.

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?

All three parameters are documented in the schema with adequate descriptions. The tool description reinforces these by showing example values for `value`, explaining accepted formats and typical usage for `since`, and clarifying the limited enum for `type`. This adds modest extra value beyond the schema.

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 begins with concrete example queries, then clearly states it provides a change feed for a company in a time window. It enumerates the specific data sources (SEC EDGAR, GDELT→GNews, USPTO) and contrasts with the sibling tool entity_profile, making the purpose unmistakable.

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 gives explicit when-to-use scenarios (e.g., 'What's new with X') and directly advises using entity_profile when a static profile is needed instead. It also provides practical guidance for the `since` parameter ('Use "30d" or "1m" for typical monitoring'). However, it does not enumerate situations where the tool should be avoided beyond that sibling distinction.

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