search_mail

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

Annotations already cover read-only, idempotent, and non-destructive hints, lowering the burden on the description. The description adds extra behavioral context: the 1000-result limit from Microsoft and the warning that returned email text is untrusted source data. This goes beyond the annotations and is useful for the agent, with no contradiction.

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 concise sentences with no unnecessary words. The main purpose is front-loaded, followed by essential usage details and a data-safety warning. Each sentence adds value, making it highly efficient.

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 output schema, the description covers the key contextual elements: the search action, cursor handling, result limits, and the untrusted nature of returned content. It does not detail authentication or return format, but those are either covered by sibling auth tools or implied, and the description is adequate for the tool's complexity.

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 only 33%, with only the cursor parameter having a description. The tool description does not mention the query or limit parameters at all, leaving them to be interpreted solely from names and types. This does not compensate for the low coverage and provides no additional meaning beyond the schema.

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 action ('Search your own Outlook mailbox') and the resource ('Outlook mailbox') with a specific mention of 'Microsoft Graph mail search'. It distinguishes from sibling tools like list_mail_messages by the intent to search, though it does not explicitly name alternatives. This is clear and unambiguous, but lacks explicit sibling comparison.

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 usage guidance on following the cursor and the 1000-result limit, but does not explicitly state when to use this tool versus alternatives such as list_mail_messages. The usage is implied through the search intent, but no when-not or alternative tools are mentioned.

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