Pause a lead's rescue cadence

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

The description usefully discloses the destructive effect ('no further touches are sent') beyond destructiveHint=true. But it claims 'safe to call twice (a no-op once cancelled)', which is idempotent behavior while the annotations declare idempotentHint=false and the schema exposes an idempotencyKey for deduping retries — a direct conflict on retry semantics.

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?

Three short sentences, front-loaded with the purpose, then retry safety, then a concrete example — nothing padded. Minor redundancy in re-demonstrating parameters the schema already fully documents.

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?

An output schema exists, so return values need no explanation, and annotations cover safety profile; the description's job is mainly effect and idempotency, which it addresses. Remaining gaps are reversibility (can a paused/cancelled cadence be resumed?) and the relationship to the luca_cadences_pause sibling.

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 100%, with all five parameters (leadId, reason, workspaceId/workspaceSlug, idempotencyKey) documented inline, so the baseline is 3. The example call adds a small amount of value by showing leadId and reason together, but reveals nothing new about the workspace overrides or the key.

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 ('cancel a lead's running rescue cadence') plus the concrete effect ('no further touches are sent'), so an agent knows what it accomplishes. However, the verb 'cancel' conflicts with the tool name/title 'pause', and it never differentiates itself from the near-duplicate sibling luca_cadences_pause, leaving an ambiguity about which one to pick.

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 example ('lead replied elsewhere') implies the trigger scenario and 'safe to call twice' gives a retry rule, which is genuine usage guidance. But there is no explicit when-to-use/when-not, no statement of prerequisites (e.g., an active cadence must exist), and no routing versus luca_cadences_rescue_start or luca_cadences_pause.

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