search_emails

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

No annotations are provided, so the description carries the full behavioral burden. It discloses meaningful traits: default behavior (all folders searched), query semantics (plain words hit body, field targeting supported), restriction options, and the return payload linkage (folder_uid + item_id). While it doesn't discuss pagination subtleties or error cases from malformed queries, it covers the core behavioral surface well for a no-annotation tool.

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 front-loaded with purpose, then flows logically from syntax to default scope to restriction options to return value. It is slightly long, but the query-syntax examples earn their place given they materially improve the agent's ability to form correct queries. No filler or redundant restatement of schema fields.

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 there is no output schema, the description wisely discloses the key return fields (folder_uid + item_id) and their downstream use with read_email. It covers query semantics, default scope, and restriction params. Minor gaps remain, such as sorting behavior and the full shape of the response, but the description is well-proportioned to the tool's moderate complexity and 100% schema coverage.

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%, establishing a baseline of 3, and the description adds genuine value on top: concrete Elasticsearch syntax examples (subject:report, from:alice, has:attachments, is:unread, AND/OR composition) teach an agent how to construct effective queries beyond the schema's terse 'query_string syntax' note. It also clarifies the folder_uid vs folder_name distinction. This exceeds the baseline.

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 opens with a specific verb and resource: 'Full-text search of emails in the BlueMind mailbox.' This clearly distinguishes it from siblings like list_recent_emails (listing vs searching), read_email (reading vs searching), and search_events (events vs emails). The scope is precise and the differentiation from sibling tools is immediately evident.

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 provides clear operating context: the query is Elasticsearch query_string syntax, all folders are searched by default, and folder_uid or folder_name restricts scope. It also signals a downstream workflow by noting results are 'usable with read_email.' It doesn't explicitly name exclusions or when-not-to-use conditions versus alternatives, but the context is strong enough that an agent can infer appropriate invocation.

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