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

Annotations already declare destructive=true and idempotent=false, but the description goes further in domain-specific terms: a timeout produces an uncertain state that must not be retried automatically, and file support is limited to LinkedIn (email files unavailable). That is exactly the kind of behavior an agent cannot infer from the structured hints.

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?

Four sentences, front-loaded with the action, then the required inputs, then the two caveats that matter most (non-retryable timeout, file-type limits). No filler, no restatement of the tool name.

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 destructive, non-idempotent send with a nested object parameter and no output schema, the description covers approval gating, input provenance, timeout risk and file limits. The one omission is the two-step confirmation flow implied by confirmation_token ('omit on first call') and reply_as_confirmed, which the schema hints at but the description never explains.

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 100%, so the baseline is 3, but the description adds cross-tool meaning by tying `prepared` to the exact output of prepare_conversation_reply and requiring `request_key` to be stable. It adds context the schema alone does not convey, though it says nothing about reply_as_confirmed.

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 and resource ('Send one exact prepared reply to the latest inbound message') with the gating condition ('after explicit human approval') attached. It clearly distinguishes itself from the sibling prepare_conversation_reply by framing itself as the send step that consumes that tool's output.

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 an explicit precondition (human approval) and an explicit input requirement (the complete prepare_conversation_reply result plus request_key). It doesn't spell out a when-not rule (e.g. 'never call this to draft or edit'), but the routing to prepare_conversation_reply is unmistakable.

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