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

Annotations already flag this as destructive and non-read-only; the description adds real behavior: chunks are removed wholesale, search results stop returning the document immediately, and the call may return `needs_confirmation`. That confirmation signal pairs with the approvalId parameter and is the kind of context annotations cannot express.

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, each load-bearing: effect, id sourcing, replacement path, and confirmation caveat. The destructive effect is front-loaded rather than buried.

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 mutation with no output schema, the description covers the key things an agent must know: irreversibility of chunk removal, immediate search impact, and the needs_confirmation/approvalId handshake. It omits any note on failure modes or whether removal is reversible, which keeps it from a 5.

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%, so kbId, workspace, approvalId, and documentId are already documented in the schema, including the workspace-token nuance. The description only reinforces that documentId comes from workbench_kb_documents_list, adding marginal value over the structured fields.

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 ('Removes one ingested document') and adds scope detail ('and all its chunks'), which cleanly separates it from workbench_kb_delete (whole KB) and workbench_flows_delete. An agent can pick it out of the densely populated workbench_kb_* family without opening the 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?

Gives concrete preconditions ('Get the documentId from workbench_kb_documents_list') and a workflow alternative for replacement ('remove it then workbench_kb_add_documents the new version'). It lacks an explicit when-not statement (e.g., when to use KB-level delete instead), so it stops short of a 5.

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