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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces rather than contradicts them. It goes beyond the annotations by disclosing that the response includes whether this server can send email at all, and that reminder rendering is conditional on sent status plus an outstanding balance.

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 preview nature and the returned fields are front-loaded, and the no-side-effects claim closes the description. The middle semicolon chain ('with the personal message and the language if given; a reminder reads differently...') is dense but each clause carries distinct information.

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 no output schema, the description carries the burden of describing the return value and does so: address, subject, text, and a server email-capability flag. For a 5-parameter read-only preview it gives the agent everything needed to call it and interpret the result.

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 100%, so the baseline is 3, but the description adds real meaning: it links 'the personal message' to message, 'the language if given' to locale, and explains the conditional semantics of reminder. That is useful cross-parameter context the schema's one-line descriptions do not supply.

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 ('Shows') and resource (the client email for a draft or sent document) and enumerates what it returns: address, subject, text. The clause 'Sends nothing and changes nothing' separates it from the send_invoice/email_invoice siblings without the agent needing to open 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?

Usage is implied rather than stated: the agent can infer this is the preview to run before sending, and the note that 'a reminder reads differently for a sent invoice with a balance' hints at the sent-vs-draft condition. However there is no explicit 'use this before send_invoice' or 'do not use to actually send' instruction naming alternatives.

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