knowledge_document

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

Annotations already indicate destructiveHint=true and readOnlyHint=false, so the agent knows this mutates. But the description does not mention overwrite behavior, wiki update plan side effects, or document review semantics. With zero descriptive behavior beyond 'write or review,' the agent gets little insight into what changes are made.

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 description is extremely short (8 words), which is concise, and the action enum values add meaningful precision. But it is under-specified rather than efficiently complete, so it doesn't earn a 5.

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?

With 12 parameters, 8% schema coverage, a true output schema, destructive annotations, and seven sibling tools, the description should explain what an evidence-backed document is, when to use each action, and what side effects occur (overwrite, wiki plan, file writes). It addresses almost none of that.

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 very low (8%) and 12 parameters exist, so the description carries almost none of the explanatory burden. However, the action description ('write=save Markdown; review=delivery check') does add meaning for two params. Most parameters—content, language, overwrite, diagram_mode, project_name, client_facing, required_sections, include_wiki_update_plan—are not explained anywhere in the description, so the score is at best a 3.

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 description says the tool writes or reviews evidence-backed documents, with action enum distinguishing write=save Markdown and review=delivery check. It is somewhat broad ('documents') given the knowledge_* sibling family, but the action enum and document_type parameter give it enough shape. It doesn't clearly distinguish itself from siblings like knowledge_page or knowledge_document_context.

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?

No explicit when-to-use guidance, no alternatives mentioned, and no context about when write vs review should be chosen beyond the schema's one-line enum meaning. The sibling list invites comparison but the description provides no routing cues.

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