Search messages

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds ordering semantics (newest first), the shape of the return value (UIDs), and a genuine security warning that sender names and subjects are untrusted email content — that last item is real added value an agent could not infer from annotations. It does not mention pagination or whether results are capped beyond the schema's limit field.

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, no filler, with the core purpose and ordering front-loaded and the return-value/security notes trailing. Every clause carries information the agent needs.

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?

This is an 8-parameter tool with no output schema, and the description compensates by stating that results are UIDs and in what order — exactly the missing return-value information. Combined with the untrusted-content warning, the picture is nearly complete; only result-set size/truncation behavior is left unstated.

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 88%, so the schema already documents all eight parameters with defaults and formats. The description's enumeration of filters (sender, recipient, subject, date, unread state) largely restates that, though it does add the otherwise-undocumented fact that results come back newest first. Baseline 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?

Names a specific verb and resource (find messages), the scope (in a folder), the ordering (newest first), and the exact filter dimensions. The second sentence names what it returns (UIDs) and which siblings consume them, so an agent can distinguish it from get_message without opening a schema.

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 'Returns UIDs for get_message, reply, mark and move' clause establishes this as the discovery entry point in a search-then-act pipeline, which is clear routing guidance. It stops short of explicit exclusions (e.g. 'use get_message when you already have the UID' or 'use list_folders to discover paths'), so it is strong but not a full when/when-not statement.

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