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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description goes far beyond by detailing the exact data sources (SEC EDGAR, GDELT→GNews fallback, USPTO with soft-fail note), the fallback mechanism, and the return format (changes[] grouped, total_changes count, citation URIs). This provides full behavioral transparency.

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 detailed but front-loaded with concrete examples. Every sentence adds value (source details, fallback, parameter guidance, alternative tool). It is not overly verbose given the complexity. One could argue minor trimming, but overall well-structured.

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 no output schema, the description covers return structure (changes[] grouped, total_changes, citation URIs). It explains the data sources and their behavior (GDELT preferred, GNews fallback, USPTO soft-fail). It even notes PatentsView API sunset. For a tool with three parameters and multiple sources, this is fully complete.

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?

Schema covers 100% of parameters, but the description adds meaningful context: it explains the `since` shorthand formats (ISO date, relative like '7d', '30d', '3m', '1y'), gives a recommended default ('Use "30d" or "1m" for typical monitoring'), and clarifies that `value` accepts tickers or CIK. This adds value beyond the schema 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 begins with concrete example queries like 'What's new with X' and clearly states it returns a 'change feed for a company in the last N days/weeks/months in ONE parallel call'. It explicitly distinguishes from sibling tool 'entity_profile' which provides a static profile. This makes the purpose highly specific and distinguishable.

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 usage context: it is for temporal, news-like queries about recent changes. It also includes a concrete alternative: 'Use entity_profile instead when you want the static profile'. This tells the agent exactly when to use this tool versus a sibling.

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