Reply and send

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

Annotations indicate destructiveHint=true, but the description goes beyond by explaining that the server sets threading headers, subject, and recipients, and that the original is quoted automatically. It also discloses the important precondition of the owner's permission, which is not in the annotations. A small gap is that it doesn't mention whether the action is reversible, but it covers key behavioral aspects.

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 description is a single, dense paragraph that front-loads the critical information: it defines the tool, states the exclusivity condition, points to the alternative, and gives the consent gate. Every sentence earns its place with high information density and no fluff.

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?

Given the tool's complexity (9 params, no output schema), the description is quite complete. It covers the key trigger condition, differentiates from siblings, and clarifies some parameter nuances. It could mention what the return value is, but with no output schema that's not strictly required. The description does enough for the agent to use it correctly.

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 89%, so the schema already explains most parameters. The description adds value by clarifying that the 'text' parameter should be plain text without greeting-to-quote artefacts, and that the original is quoted automatically, which helps the agent avoid duplication. It also clarifies that 'attachments' can be mailbox attachments, inline content, or local files, which is important for correct invocation.

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?

The description clearly states this tool sends a reply to a specific message, and explicitly differentiates it from reply_draft and other send-related tools by mentioning the threading and quoting handled by the server. It uses a specific verb ('sends') and names the target resource ('a reply to a specific message').

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?

The description gives explicit when-to-use vs when-not-to-use: 'Only when the owner enabled sending for the account AND every recipient matches send_allowlist; otherwise use reply_draft.' It also includes the critical consent gate: 'Use this only when the owner says "send".' This is exceptional usage guidance.

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