Send a message to a lead

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

Annotations already carry destructiveHint=true and idempotentHint=false, but the description adds meaningful context beyond them: the reviewer-bypass nature, the required confirm: true gate, idempotency-key generation behavior, required scopes (conversations:write, luca:queue_ops), data sensitivity (redacted), and workspace override semantics. This is a genuinely rich behavioral disclosure for a side-effecting 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?

The key scoping and review-queue guidance is front-loaded in the first two sentences. The remaining lines are operational metadata (operation path, scopes, sensitivity) that is useful but somewhat templated and repetitive of the confirm parameter description.

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 complex, nested, destructive send tool with an output schema and full annotations, the description covers purpose, prerequisite confirm, idempotency, scopes, and workspace scoping. It leaves the body content part types (text/media/interactive/template) to the schema, which is acceptable given schema and output-schema richness.

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 67%, which sits in the mid band where the schema largely documents the parameters (confirm, workspaceId, workspaceSlug, idempotencyKey all carry descriptions). The description restates idempotency and workspace behavior rather than adding syntax or format detail beyond the schema, so baseline 3 is appropriate.

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 ("Send a message to the lead on their channel right away") and distinguishes itself from the review-queue flow by noting it is "the one conversation tool that reaches a real person without a reviewer seeing the message first." It does not name the specific alternative sibling tool (e.g. a review_queue/approve tool), so the differentiation is by category rather than by name.

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 when-not: "Prefer drafting into the review queue unless the coach has asked for this message to go out now." This is a real selection rule an agent can act on. It stops short of naming the concrete alternative tool, so a 4 rather than a 5.

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