search_messages

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

With no annotations provided, the description carries the full behavioral burden and does so well: it discloses that results are not sorted, that Graph caps results at about 250, that nextLink is needed for further results, and that subjects, senders, and previews are untrusted content that must not be followed as instructions. This is rich, operationally important context beyond the schema.

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 three tightly written sentences. It front-loads the core purpose and example, then adds operational constraints and a security warning, with no wasted wording.

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 search tool with no annotations and no output schema, the description covers the most important behavioral traits: unsorted results, result cap, pagination, and untrusted email content. It still leaves top unexplained and does not describe the overall return shape beyond the untrusted key, so it is strong but not fully complete.

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 only 50%, and the description adds useful meaning for query (KQL syntax with examples) and nextLink (pagination continuation). It does not explain the top parameter at all, and folderId meaning is left to the schema description, so it only partially compensates for the coverage gap.

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 states a specific verb and resource: full-text search of messages using KQL, with an example query. It is clear what the tool does, but it does not explicitly distinguish itself from the sibling list_messages tool.

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?

Usage is implied by 'Full-text search using KQL', and pagination guidance is given via nextLink. However, the description does not say when to use this tool instead of list_messages or other message-retrieval siblings, nor does it state any exclusions.

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