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

Beyond annotations (readOnlyHint, idempotentHint), the description details multi-source fan-out, fallback logic (GDELT→GNews), soft-fail for USPTO, and return structure with citation URIs. It fully discloses how the tool behaves.

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 front-loaded with example queries and is information-dense. While it is lengthy, every sentence adds value. Slightly more structural formatting (e.g., bullet points) could improve, but it remains concise relative to the 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?

Given the absence of an output schema, the description explains the return structure (grouped changes, total count, citation URIs). It also covers parameter formats, fallback behavior, and sibling differentiation, leaving no apparent gaps.

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 provides detailed descriptions for all three parameters (100% coverage). The tool description adds context on how 'since' affects the feed and offers default suggestions, but the schema already handles most 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 states it returns a 'change feed for a company' within a time window, listing data sources and explicitly distinguishing from the sibling tool 'entity_profile' which provides static profiles. The purpose is specific and unambiguous.

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 example queries, specifies the time window context, and directly advises when to use 'entity_profile' instead. This gives clear guidance on appropriate usage versus alternatives.

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