message_send_propose

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

Beyond the boolean annotations (all false), the description discloses a real behavioral trait: Telegram attaches approve/cancel buttons to this proposal. It also adds the operational instruction not to paste the letter into chat, which is useful context an agent would not get from the schema or annotations. It does not go into what happens after an approve, but the word 'preview' plus approve/cancel sufficiently conveys the interaction model.

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?

Two short, purposeful sentences. The purpose is front-loaded in the first sentence, and the second sentence supplies the critical Telegram behavior and a safety instruction. There is no filler or repetition.

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 simple 3-string-parameter proposition tool, the description explains the workflow (preview, approve/cancel, avoid pasting body content) well enough for an agent to invoke it sensibly. It lacks parameter detail and does not specify the post-approval effect, but the approve/cancel model and the tool's propose semantics cover the main decision point.

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 0%, so the description should compensate for the undocumented to/subject/body parameters. It only indirectly refers to 'the letter' and 'Gmail', providing weak semantic context, but it never clarifies the meaning or format of individual parameters. An agent still has to infer that 'to' is a recipient email address and 'subject' is an email subject.

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 opens with a specific action and resource: 'Preview sending Gmail.' It clearly identifies the tool as the approval-gated send proposition for email, and the mention of Telegram approve/cancel distinguishes it from a plain drafting tool like message_draft. The purpose is unambiguous from the first sentence.

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 clear context for use: this is the preview/send-proposal path for Gmail, and it explicitly warns the agent not to paste the email body into chat. It does not enumerate exclusions or name alternatives like message_draft, so it falls just short of fully explicit when-not-to-use guidance.

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