Undo a call's outcome

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description goes beyond them by disclosing the 48-hour undo window, the required scope (call_events:write), the data sensitivity, and how idempotency is achieved via a server-generated key on retries – the last point usefully reconciles the idempotentHint=false annotation rather than contradicting it. It does not say what state the call is restored to beyond "back in the queue".

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 purpose and window are front-loaded in the first sentence, followed by operational metadata. It is compact overall, though the idempotency sentence duplicates the input-schema description of idempotencyKey and the API/scope lines are boilerplate.

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?

This is a destructive mutation, but annotations cover the safety profile and an output schema exists, so return values needn't be explained. With the window, auth scope, idempotency handling, and workspace override all documented, an agent has nearly everything needed to call it correctly; only the post-undo state and failure cases are left implicit.

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 75%, so the schema already explains workspaceId, workspaceSlug, and idempotencyKey. The description largely repeats those same facts (idempotency key generation, workspace override) without adding format or edge-case detail, so the baseline of 3 for schema-documented parameters applies.

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?

"Clear a mistaken attendance mark and put the call back in the queue" gives a specific verb (clear/undo), the resource (call outcome / attendance mark), and the resulting state change. An agent can distinguish this from siblings like luca_call_events_feedback or luca_bookings_outcome_record without opening any schema.

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?

The description states the triggering condition (a mistaken attendance mark) and a hard eligibility constraint (48 hours from when the outcome was set), which is exactly the kind of context that determines whether an agent should attempt the call. It does not, however, name a sibling as the alternative for when the window has elapsed or for re-recording instead of undoing.

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