conduyt_reply_suggestion_decide

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

With no annotations, the description carries the full burden and does real work: it discloses the one-transition lifecycle rule ('A suggestion moves once (accepted → sent is allowed)') and the refusal condition for unconfirmed outbound ids. It doesn't state idempotency/retry behavior or whether repeat calls error, which is the main remaining gap for a mutation tool.

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?

One dense, front-loaded block: the action and its scope come first, then the per-value conditions, then the state-machine constraint. No filler sentences and nothing repeated from the schema.

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 4-parameter mutation with no annotations and no output schema, the description covers intent, per-decision preconditions, and the transition rule. It stops short of describing what the response contains or what downstream effects recording a decision has (e.g. whether future suggestions are suppressed).

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 75%, and the description adds semantics the enum alone cannot convey — what each decision value means operationally and that sentMessageId must be outbound and provider-confirmed, tying the parameter to its precondition. The contactId/messageId linkage is left to the schema descriptions.

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?

States a specific verb+resource ('record what was done with a suggested reply') and enumerates the exact three recordable outcomes with their meanings. An agent can distinguish this outcome-recording tool from conduyt_reply_suggestion (which generates the draft) without opening either schema.

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?

Gives explicit when-to-use guidance per decision value: 'accepted' when the draft was taken into a composer, 'sent' only after actually sending via conduyt_send_message / the messages API, 'dismissed' otherwise. It also names the ordering constraint that selects the accepted→sent path.

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