email_triage

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

No annotations are provided, so the description carries the full burden. It mentions return values but does not disclose potential side effects (e.g., changing read status or labels) or any required permissions. This lack of detail leaves behavioral ambiguity.

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 short (two sentences) and directly states the tool's purpose. However, the second sentence ('Use with an AI agent to auto-process') is somewhat redundant and could be integrated or omitted.

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 and no annotations, the description should provide more context about the return format, classification criteria, or behavior for edge cases. The current description is too brief for an agent to fully understand the tool's operation.

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 coverage is 100% with clear parameter descriptions. The tool description does not add further meaning beyond the schema, so the baseline score 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?

The description clearly states the tool 'Triages unread emails' and specifies return values including priority classification and suggested actions. This distinguishes it from siblings like email_read (just read) and email_suggest_reply (only suggestions).

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 tool indicates it is for processing unread emails and suggests use with an AI agent. However, no explicit guidance on when not to use it or comparison to alternatives like email_inbox or email_suggest_reply is provided.

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