Extract Action Items

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

Annotations indicate readOnlyHint=true, and description adds behavioral context: it's heuristic, best-effort on assignee/due-date, and non-destructive. It does not contradict annotations and provides sufficient transparency about the tool's limitations and behavior.

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?

Three sentences, no wasted words. Front-loaded with the core function, immediately followed by caveats. Each sentence earns its place.

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 3 parameters, presence of output schema, and readOnlyHint annotation, the description is complete. It explains what the tool does, its limitations, and usage context without needing to detail return values (handled by output schema).

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 description coverage is 100% with each parameter clearly described (folder, email_id, account_id). The tool description does not add additional meaning beyond what the schema provides, so baseline of 3 is appropriate.

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?

Description clearly states it scans an email body for action-item-looking lines (bullets, TODO markers, @mentions) and returns structured list. Distinguishes itself from a real task extractor by noting it's heuristic and for quick triage. This leaves no ambiguity about its purpose.

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?

Explicitly says it's not a replacement for a real task extractor and useful for quick triage, giving when-to-use and when-not-to-use guidance. However, it does not mention specific alternatives or sibling tools like extract_meeting for comparison, so it could be more explicit.

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