Disconnect a knowledge source

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

Beyond the destructiveHint already in annotations, the description discloses exactly what is destroyed (pending suggestions), what survives (approved profile values), the required scope (knowledge:write), the OAuth scope, and the idempotency-key requirement including the server-generate fallback. This is unusually rich for a destructive mutation.

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?

Purpose and side effects are front-loaded in two tight sentences; the metadata block that follows is dense but each line (scope, sensitivity, idempotency, workspace override) carries actionable information. Minor redundancy between the idempotency sentence and the schema description.

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. The description covers the mutation's blast radius, authorization requirements, retry semantics, and workspace targeting — everything needed to call this destructive endpoint correctly.

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% and already documents workspaceId, workspaceSlug, and idempotencyKey. The description adds real meaning on top: it explains the retry-safety semantics of idempotencyKey and the workspace-override intent, rather than merely restating field names.

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?

The first sentence gives a specific verb (delete/disconnect) and resource (knowledge source), then immediately explains the semantic consequence of deletion — pending suggestions are removed, already-approved values persist in the profile. This separates it cleanly from siblings like luca_knowledge_sources_sync and luca_knowledge_sources_list.

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?

Usage is implied by the deletion semantics and the note about overriding the default workspace, but the description never states when to choose disconnect versus sync/list, nor any precondition (e.g., what happens to an in-flight sync). The agent must infer the context of use.

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