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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false, so the safety profile is covered. The description adds context annotations cannot carry: the action opens a draft in the local macOS Mail client rather than sending, and it requires a specific OAuth scope plus possible interactive owner approval. It stops short of saying what happens on repeated calls (whether duplicate drafts accumulate) or what is returned, which keeps it at 4 rather than 5.

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?

Three short sentences, no filler, and the non-sending constraint is front-loaded right after the action statement. The alternative-tool routing and the auth requirement each occupy one clause rather than their own throat-clearing sentence.

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 3-required-parameter mutation tool with no output schema and full annotation coverage, the description covers the essentials: what it creates, what it does not do, the alternatives, and the auth/approval gates. What is missing is post-call behavior — whether the draft persists, where it surfaces, and duplicate-call semantics — which matters given idempotentHint=false.

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 the baseline is 3 and the description adds nothing about to/subject/body. Notably the schema's own description for "to" reads "New destination path; overwrites are refused…," which looks like a file-path description leaked from another tool, and the description does not correct that mismatch — an agent could misread the recipient semantics.

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 and resource ("Open an editable draft in macOS Mail") and immediately bounds scope with "It does not send email." The naming of exza_preview_email_message and exza_send_email_message makes the boundary against the two closest siblings unambiguous without opening any 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?

Gives explicit when-to-use (draft for review) versus the alternatives: preview via exza_preview_email_message for inspection, exza_send_email_message only for explicitly approved sending. It also states the preconditions ("after approval," account-bound computer:write OAuth, prompted local owner approval), so an agent knows both the routing decision and the gating requirements.

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