read_message

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

Annotations cover the safety profile (readOnly, non-destructive, openWorld), yet the description adds genuinely non-obvious behavior: reading does NOT set the Seen flag, content is never executed, bodies are truncated and must be checked, and attachment file download is unavailable in v0.1. These are exactly the traits an agent cannot infer from annotations or schema.

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 tight sentences with no filler, and the highest-value constraints (no Seen mutation, no content execution, bounded bodies) are front-loaded. Nothing restates the tool name or annotations.

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 still conveys the return shape (MIME text, attachment metadata, a truncated flag) and the v0.1 capability limit. It leaves mailbox defaulting and max_chars interaction with truncation unstated, which is a minor but real gap for a four-parameter tool.

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 0%, so the description must compensate, and it does for the most error-prone parameter: message_id is opaque and must come from search and match its original account/mailbox, which constrains account_id and mailbox too. max_chars is only indirectly explained via 'bodies are bounded; check truncated', leaving some gap.

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 (MIME text and attachment metadata), and adds a discriminating scope clause ('without setting Seen') that separates it from mark_read. It does not name a sibling directly, but the scope statement makes the boundary inferable 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 a concrete calling prerequisite: use the opaque message_id returned by search, in its original account/mailbox. That is clear context for correct invocation, but it never states when to prefer this over search_messages or mark_read, and gives no explicit exclusions beyond the attachment-download limitation.

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