Dismiss a learning proposal

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

Goes well beyond the annotations by disclosing required scopes (learning:write, luca:draft), redacted data sensitivity, the mandatory Idempotency-Key and the server-generated fallback, and workspace override behavior. The annotations already cover the destructive/idempotent/openWorld profile, so the added auth and retry context is the real value. It stops short of saying whether a dismissed proposal can be restored.

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 behavior is front-loaded in the first sentence, with the operational metadata (endpoint, scopes, idempotency, workspace) following in a tight block. Slightly list-like and repetitive of the schema for the idempotency key, but every line carries information.

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 an output schema present, return values need no explanation, and the description supplies auth, sensitivity, idempotency, and workspace context. The one notable gap for a destructiveHint=true tool is whether dismissal is reversible or how it relates to the proposal list/panel siblings.

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%, so the schema already documents the parameters, but the description contributes the fact that workspaceId/workspaceSlug override an environment-configured default workspace and that the idempotencyKey exists specifically for safe retries. That is meaningfully more than the terse schema strings.

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 ('Dismiss one learning proposal') plus the observable effect ('drops out of the default list'), which implicitly distinguishes it from read-only siblings like luca_learning_proposals_list. An agent can tell this is a state-changing dismissal, not a fetch.

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?

Explicitly gates the call on intent: 'Use it when the coach has decided against the change, not when you have simply read it.' That is a clear when-to-use plus a when-not, though it never names the alternative tools (e.g. the proposals list/panel) that cover the reading case.

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