conduyt_reply_suggestion

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

No annotations are present, so the description carries the full burden; it discloses the important non-mutation guarantee ('nothing is sent') and explains state semantics including opt-out, do-not-contact, and feature-off cases. It does not disclose whether reading changes a pending state, permission requirements beyond the schema note, or error behavior.

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?

It is front-loaded with the resource and scope, then the safety caveat and state legend, with little wasted text. The unexplained 'Copilot Tier 2' label is minor but slightly opaque.

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?

With one parameter, no output schema, and no annotations, the description is the main source of return-value and safety context; it covers the content returned and the possible states. Gaps remain around exact return shape and whether a read transitions state, but it is largely complete for an advisory read tool.

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?

Only contactId exists, and schema coverage is 100% with its own description ('Contact UUID (must be visible to the caller)'). The description adds only 'for a contact's latest inbound text or email,' which scopes the contact but does not add formatting or selection detail beyond the schema.

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 names the exact resource and scope: the suggested reply for a contact's latest inbound text or email, including what was said, what is asked, sentiment, and a draft reply. It clearly rules out sending with 'nothing is sent,' though it does not explicitly distinguish itself from conduyt_reply_suggestion_decide.

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?

It tells the agent this is advisory only, that it looks at the latest inbound item, and it explains state values such as pending, decided, and skipped. However, it does not explicitly state when to choose this tool over conduyt_reply_suggestion_decide or other AI/conversation tools.

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