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

Annotations already declare readOnlyHint and idempotentHint, but the description adds substantial behavioral detail: fan-out to three sources, GDELT-to-GNews fallback on rate limiting/5xx, USPTO soft-fail due to PatentsView API sunset, and the return structure with pipeworx:// citation URIs. No contradiction with 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 a single dense paragraph that packs a lot of valuable information: query examples, sources, fallback logic, parameter formats, return shape, and an alternative tool. It is not overly verbose, but the density could be slightly improved with bullet points or clearer separation of sections, so it earns a 4 rather than 5.

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 compensates by naming the return fields (changes[], total_changes, pipeworx:// URIs), explaining source behavior, and giving fallback and alternative-tool guidance. An agent has enough context to select this tool, set parameters correctly, and interpret the result.

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 practical parameter guidance: it explains that 'since' accepts ISO dates or relative shorthand like '7d' and '3m', and clarifies that 'value' can be a ticker or zero-padded CIK. The type restriction to 'company' is reinforced, going beyond the schema's enum.

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 uses a specific verb phrase ('change feed for a company') and clearly names the sources (SEC EDGAR, GDELT/GNews, USPTO) and the output (changes[] with total_changes and citations). It differentiates itself from sibling tools by explicitly directing users to entity_profile 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 example intents ('What's new with X', 'latest on Y') and states the window format. It also says to use entity_profile instead when a static profile is needed, which is a clear alternative. The fallback behavior between GDELT and GNews is described, helping the agent decide when to call this tool.

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