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

With only destructiveHint=true in the annotations, the description carries the behavioral burden and delivers: it warns 'MUTATES KnowledgeOwl data,' discloses the API contract, and importantly flags that the API requires six fields (type, project_id, url_hash, name, visibility, status) even though the schema only marks two as required. It also states the return behavior ('Returns the created category'), which matters given there is no output schema.

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?

Five dense sentences, each earning its place: mutation warning, purpose, endpoint, API-required fields, fields escape hatch, and return value. The mutation flag is front-loaded and there is zero 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 7-parameter tool with no output schema, the description covers purpose, mutation, endpoint, required inputs, the fields mechanism, and the return value. Minor gaps remain: no prerequisites (e.g., how to obtain project_id), no explicit pointer to update_category for edits, and no mention of error behavior when API-required fields are omitted.

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 the baseline is 3, but the description adds real value by listing which fields the API actually requires — correcting the schema's impression that only project_id and name matter — and by explaining how to funnel extra documented fields through the 'fields' object. This guides parameter selection beyond what the schema alone provides.

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 states a specific verb and resource — 'creates a new category' — and grounds it in the domain as 'a node in the article tree,' which distinguishes it from sibling tools like create_article and create_glossary_term. The explicit API endpoint (POST /category.json) further pins down the operation.

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: an agent would naturally select this to create a category. However, the description offers no explicit when-to-use/when-not-to-use guidance and never names alternatives such as update_category for modifying an existing category, leaving sibling routing to inference.

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