read_message

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

With no annotations present, the description carries the full burden and handles the two highest-risk behaviors: it declares the read is non-mutating (doesn't set the read flag) and flags the body as untrusted third-party text with an explicit instruction not to follow embedded commands. It omits other behavior an agent would want — truncation of long bodies, behavior for a nonexistent uid, and that attachments are named but not downloaded.

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, front-loaded with the action and payload, then the side-effect disclaimer, then the safety warning. No filler and nothing buried.

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?

No output schema and no annotations, so the description must define the return surface itself, and it does list the returned parts. Slightly short of complete because the max_chars truncation contract and error behavior on a bad uid are unaddressed for a tool whose sole required parameter is undocumented in the schema.

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 only 33% — folder has a description but uid and max_chars do not. The description explains uid (the message identifier to read by) but says nothing about max_chars, which silently truncates bodies at 20k chars by default, nor about the default INBOX folder. It compensates partially, not fully, for the coverage 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?

"Read one message by uid" names a specific verb and resource with an explicit cardinality constraint, then enumerates exactly what comes back (headers, plain-text body, attachment names). That enumeration distinguishes it from bulk siblings like search_messages and list_folders without needing to name them.

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 by "by uid", which tells the agent a uid must already be known and that discovery belongs elsewhere, but no sibling is named and no when-to-use/when-not rule is stated. The "does not mark it read" clause implicitly routes to mark_read but never says so explicitly.

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