Reply to the customer (SENDS AN EMAIL)

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

The description adds substantial behavioral context beyond the annotations: 'cannot be unsent' reinforces destructiveHint=true, and the two-step preview explains that a retry costs a preview, not an email. It also details what the preview returns (recipients, subject line, rendered HTML), making side effects transparent.

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 concise paragraphs front-load the critical warning about emailing the requester, then explain the two-step flow, and end with an alternative. Every sentence earns its place; there is no repetition or filler.

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 moderate complexity and no output schema, the description covers the essential behavioral contract: what is sent, the preview/send flow, safety against accidental sends, and the appropriate alternative for human approval. It is complete enough for an agent to use correctly without further clarification.

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?

The description adds meaning for the confirm parameter ('called without confirm... returns a preview; call it again with confirm:true to actually send'), and the preview mention implies cc_emails/bcc_emails are included in recipients. However, it does not elaborate on from_email, cc_emails, or bcc_emails beyond the schema's existing descriptions. With 50% schema coverage, this is adequate but not exceptional.

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 verb+resource: 'Send a public reply on a ticket.' It immediately clarifies the key distinction from sibling tools by emphasizing 'THIS EMAILS THE REQUESTER and cannot be unsent,' which differentiates it from freshdesk_add_public_note and freshdesk_add_private_note.

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?

Provides explicit usage guidance: the two-step confirm flow with preview, and a clear when-not-to-use directive: 'If a human is supposed to approve the wording, do not use this at all: put the draft in freshdesk_add_private_note and let them send it.' This names an alternative and defines the boundary.

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