Start a CRM sync

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

Adds substantial context beyond annotations: required scopes (integrations:write, luca:full), data sensitivity (full_content), the Idempotency-Key requirement with server-side fallback, and the hard rule that the call is rejected without confirm: true. The annotations declare destructiveHint and idempotentHint, but the description is what tells the agent exactly how to satisfy them.

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-loaded with the action, then layered operational facts as short lines. The idempotency sentence is slightly redundant (name requirement, then explain fallback), but overall it is tight and scannable rather than verbose.

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 the description covers the mutation's safety, scoping, and auth requirements thoroughly. The only real gap is semantics of mode/direction, which the agent must infer from the enum names.

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% and the schema already documents confirm, idempotencyKey, workspaceId and workspaceSlug richly. The description largely restates those and offers no extra meaning for the mode/direction parameters (defaults and allowed values live only in the schema), so it sits at the baseline.

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 ('Create a CRM ... sync run') and further qualifies scope with 'dry-run or live', distinguishing it from the read-side sibling luca_integrations_crm_sync_runs_list without ambiguity. An agent immediately understands this starts a sync run.

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 implies usage (create a run, pick dry-run vs live) but never states when to prefer this over the list tool or what prerequisites must be met before a run is meaningful. Operational rules (scopes, idempotency, confirm) are present, so usage is inferable but not explicit about alternatives or exclusions.

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