Disconnect a CRM

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

Goes well beyond the annotations: it discloses exactly what is destroyed (credentials) versus retained (mappings, event history), the resulting state (all syncs stopped until reconnect), the confirm:true gate with rejection on omission, the Idempotency-Key behavior including server-side generation, and required scopes. This is consistent with destructiveHint=true and idempotentHint=true rather than merely restating 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?

The first paragraph is front-loaded with the semantic payload and the operational lines (endpoint, scopes, idempotency, confirm, workspace override) are scannable. It is slightly long, with some redundancy between the prose and the schema's parameter descriptions.

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 destructive connection-mutation tool, everything an agent needs is present: effect, reversibility path, retention of data, confirmation requirement, retry safety, permissions, and workspace override. An output schema exists, so return values need no explanation here.

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 80%, so the baseline is 3. The description largely echoes the schema's own text for confirm and idempotencyKey; the only genuine addition is that workspaceId/workspaceSlug override a default workspace set by the environment.

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 ('Disable a CRM connection and clear the credentials Luca holds') plus the concrete consequence ('stops every sync with that CRM until the coach connects it again'). It also bounds the effect ('Saved mappings and event history stay', 'does not revoke access on the CRM's side'), which distinguishes it from a sibling like luca_knowledge_sources_disconnect and from any CRM-side revocation.

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 scope of use is clear: this is the tool for halting syncs while preserving configuration, and the note that it does not revoke CRM-side access implicitly points at when a different action is needed. However, no alternative sibling tool is named (e.g., reconnect/health/sync-run tools) and no explicit 'use when / don't use when' routing is given.

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