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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed world), so the description's contribution is the behavioral detail it adds: a hard cap of 100 messages and the fact that codes and links are pre-extracted, which tells the agent it needn't parse or fetch per-message. It does not disclose ordering or whether the read is destructive to unread state, which keeps it short of a 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?

A single sentence, front-loaded with the action and scope, followed by the returned fields. No filler, no restatement of the tool name.

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 return-value burden and does so by enumerating the per-message fields. The remaining gaps are pagination/ordering beyond the 100 cap and whether reading mutates inbox state, both of which matter for a list tool but are minor given the size limit is stated.

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 both parameters (id, token) are already fully documented in the schema, including the anonymous-resource token case. The description adds nothing about either parameter, so the baseline 3 applies.

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 ('Read') and resource ('every message in an email inbox') plus the concrete payload an agent gets back (sender, subject, text, HTML, codes, links, attachment names). This clearly separates it from wait_for_email and get_email_attachment, though those siblings are never named.

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 only implied: an agent can infer this is the tool for bulk inspection of an existing inbox rather than waiting for new mail or fetching a single attachment. There is no explicit 'use this when... / use X instead when...' guidance, and nothing says whether calling it consumes or marks messages as read.

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