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

Annotations only carry destructiveHint=true, so the description does the heavy lifting: it declares mutation, discloses partial-update semantics (omitted fields are untouched), and states that `fields` entries are merged OVER the typed fields. It does not cover permissions, reversibility, or error behavior on a bad id, which keeps it from a 5.

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, mutation warning front-loaded, followed by endpoint and then the two non-obvious mechanics (partial update, id not in body). No filler.

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 6-parameter destructive mutation with a nested `fields` passthrough and no output schema, the description covers the mechanics an agent most needs: partial update, merge order, and id handling. It is silent on failure modes (nonexistent id, validation errors) and what the call returns, which are the remaining gaps.

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 100%, so each parameter is already documented. The description adds one genuinely new detail — that the path id is never sent in the body — but the merge-precedence note for `fields` merely repeats the schema text, so it is roughly at the high-coverage 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 (updates) and resource (existing category), and explicitly flags it as a mutation of KnowledgeOwl data. The 'existing' qualifier plus the PUT endpoint make it clearly distinct from sibling knowledgeowl_create_category and knowledgeowl_update_article.

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 partial-update usage ('only included fields change') and tells the agent to route undocumented fields through `fields`, which is real usage guidance. However, it never states when to use this versus knowledgeowl_create_category or knowledgeowl_get_category, nor any prerequisites such as the category needing to exist.

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