Turn auto-send on or off for a channel

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

Goes well beyond the annotations by disclosing the cascade side effect ('also turns on the workspace switch, so every other account with its own switch on starts sending too'), the review-queue consequence of disabling, unsupported-account behavior, required scopes, and the confirm/idempotency requirements. This is exactly the extra context destructiveHint=true alone cannot convey.

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?

Front-loads the core behavior in the first two sentences, then a compact metadata block for operation, scopes, and safety. Slight redundancy where idempotencyKey and confirm are re-explained relative to the schema, but no wasted framing.

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 mutation with cascading, cross-account effects, the description covers the write behavior, the fallback path, the unsupported-channel case, the required confirmation, and the auth scopes. An output schema exists, so return values need not be explained.

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?

Adds real meaning to the `enabled` boolean (on = bypass review plus workspace-wide cascade; off = route to review queue) that the bare schema does not. It also restates the idempotencyKey, confirm, and workspace-override semantics, though those are already covered in the schema descriptions at 67% coverage.

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 with scope: 'Turn Luca's DM auto-send on or off for one channel account.' The 'one channel account' scope and the DM-auto-send resource distinguish it cleanly from sibling channel tools like luca_channels_get and luca_channels_list.

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?

Explains the consequences of each mode ('Off puts every Luca draft on that account in the review queue', 'On lets drafts that pass Luca's safety checks send without review'), and gives explicit boundary cases ('Campaign sends follow their own policy. WhatsApp and disconnected accounts answer 404'). It stops short of naming a sibling alternative to use instead, but the conditional context is strong.

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