search_emails

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

The readOnlyHint annotation already indicates a safe read operation. The description adds behavioral context by mentioning 'live IMAP filters', 'optional local post-processing', and implicitly that Bridge IMAP availability is required (since the alternative works without it). This goes beyond the annotation, though it does not mention potential latency or result size implications.

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?

Two sentences deliver the core purpose and usage guidance without any filler. The first sentence states the function, and the second provides decision-making context. Every word earns its place, making it highly concise and 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?

For a tool with 24 parameters and no output schema, the description covers the main purpose, when to use it, and the alternative. It does not explain return values or pagination, but the schema's 'fields' parameter and 'limit' parameter imply this. The description is adequate for a complex search tool, though a brief note on result structure would improve completeness.

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%, so parameters are fully documented in the schema. The description's mention of 'optional local post-processing for attachments and labels' conceptually groups parameters like label, threadId, and attachmentName, but the schema already notes 'applied locally' for those. Thus the description adds little beyond the schema's parameter 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 clearly states the tool 'searches emails via live IMAP filters with optional local post-processing for attachments and labels'. It distinguishes itself from the sibling search_indexed_emails by emphasizing real-time searching and local post-processing, leaving no ambiguity about what this tool does.

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?

Explicit usage guidance is provided: 'Use when you need real-time results or must find messages received after the last sync.' It also names a specific alternative (search_indexed_emails) with clear conditions and benefits, stating it is 'significantly faster and works even when Bridge IMAP is unavailable.' This fully addresses when to use this tool vs. alternatives.

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