create_reply

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

With no annotations, the description carries the full burden and does it well: it discloses body escaping, appended operator signature, the draft-by-default gate, the degraded send=True behavior when sending is disabled, and the refusal conditions (automated/no-reply senders, already-processed emails). These are exactly the non-obvious behavioral traits an agent needs before invoking a mutation.

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?

Five tight sentences, front-loaded with purpose, then format, then side-effect gating, then failure conditions. Nothing is repeated from the schema or wasted.

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?

An output schema exists, so return values need no explanation, and the description covers the remaining risk surface: side effects, degradation under operator policy, and refusal cases. The only residual gap is the identifier format, which is minor for a tool whose behavior is otherwise fully disclosed.

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 must compensate, and it does for `body` (plain text, blank-line paragraphs, HTML-escaped, signature appended) and `send` (default false, conditional send). `original_email_id` is only implied by "reply to an incoming email" — its expected format and where to obtain it are never stated.

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 opening sentence gives a specific verb and resource ("Create a reply to an incoming email") that no sibling tool duplicates. The rest of the description sharpens what kind of reply it is (draft by default, sent only under operator policy). It does not name a sibling or alternative path, so an agent gets no explicit routing contrast.

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?

Strong conditional guidance: send=False (default) saves a draft, send=True sends only if the operator enabled sending, and certain senders/emails are refused outright. That tells the agent when the tool will and won't act. It never states when to prefer escalate_to_human instead of replying, which is the one real usage decision left to inference.

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