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

Annotations already cover readOnly/idempotent/non-destructive, so the bar is lower; the description adds real value by disclosing data provenance (server's copy, not a local record) and the failure modes encoded in state: 'no_machine' and 'unavailable ... the mail copy could not be read just now.' It omits pagination or ordering behavior, but the output schema presumably covers shape.

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?

Front-loads what it does, then the use case, then the behavioral qualifiers. Every clause earns its place: provenance, returned fields, purpose, and failure states. No padding 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?

With an output schema present, the description needn't detail return values, and it already names the key fields and the state outcomes. Combined with rich annotations and a zero-parameter schema, an agent has everything needed to select and call it correctly.

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?

The tool takes zero parameters, so the baseline of 4 applies. The description correctly does not invent parameter semantics, and the state enumeration reflects the response rather than an input.

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?

States a specific verb ('Lists') and resource ('every email the MyClawn computer sent from its own address'), plus the exact provenance ('read from the mail server's copy') and the returned fields (recipient, subject, time). This is clearly distinguishable from siblings like send_file, activity, or tasks, which serve different resources.

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?

Gives two concrete use cases: 'confirm a message really went out' and 'show the user what was sent.' That is clear contextual guidance. It doesn't name an alternative tool or an explicit when-not-to-use, but no sibling appears to be a competing read path for sent mail.

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