Mail lesen

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

Annotations provide only openWorldHint, no readOnlyHint or destructiveHint. The description discloses the HTML-to-text reduction behavior, which is helpful, but it omits the markSeen side effect that can modify message state. Since the schema includes markSeen but the description does not mention it, an agent may not anticipate that calling this tool can have a write effect. Partial transparency.

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 two sentences, front-loaded with the core action and scope. Every word adds value: the first sentence defines the operation and result components; the second discloses a behavioral nuance. No fluff or repetition.

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?

Without an output schema, the description must explain the return value. It does so by listing headers, text, and attachment list. It also discloses HTML reduction behavior. It does not mention error handling or what happens if the message is not found, but for a read tool with maxChars and includeHtml parameters, the essential information is covered. Slightly incomplete regarding the markSeen side effect, but that is more behavioral than contextual.

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 all parameters are documented. The description adds a little context by specifying that output includes attachment list, but it does not elaborate on parameter meaning beyond the schema. It references 'UID' which matches the uid parameter, but adds no new semantics for account, mailbox, markSeen, maxChars, or includeHtml. 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?

The description states a specific verb (liest/reads), a resource (Nachricht per UID), and the scope (Kopfzeilen, Text, Liste der Anhänge). It clearly differentiates from siblings like mail_get_raw by mentioning parsed content and HTML reduction, so an agent can tell when to use this tool without opening the 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 description implies usage for reading parsed message content and notes HTML reduction, but it does not explicitly name alternatives or state when not to use it. For example, it does not say 'for raw email use mail_get_raw'. The context is clear but exclusion criteria are missing, so only implied guidance.

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