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

Annotations carry almost no signal — all hints are false — so the description carries the behavioral burden, and it delivers: it discloses that the type is inherited from the global record when global IDs are supplied, that a divergent type triggers a 400 error, and that parentId requires matching types. This goes meaningfully beyond the structured annotation fields.

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?

Two dense sentences with zero filler: the core purpose is front-loaded, followed by the subcategory rule and the global-catalog inheritance caveat. Every clause earns its place — the parentheticals carry real constraints rather than redundancy.

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 tool with 7 parameters, 2 required, and an output schema present, the description plus the fully-covered schema provide a complete picture of the creation variants (plain category, subcategory, global-linked). Minor gaps remain — no mention of name-uniqueness constraints or subcategory depth limits — but nothing an agent needs to invoke the tool correctly is missing.

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 the baseline is 3; the schema already documents every parameter including the type-inheritance rule on the type field. The description adds some connective meaning (the parentId type-constraint and the 400-error consequence), but it mostly re-expresses what the schema already states, so no credit above baseline is warranted.

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 opens with a specific verb+resource — "Cria uma categoria ou subcategoria do usuário" — and adds a distinguishing mechanism (parentId for subcategories), which separates it from siblings like create_transaction or create_account. The mention of the global catalog tie-in further narrows this tool's unique identity among the create_* family.

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 gives clear conditional usage context: when to use parentId (to create a subcategory), when to use globalCategoryId/globalSubcategoryId (to link to the global catalog), and the consequence of a type mismatch (400 error). It does not explicitly name alternatives like update_category or list_categories, but the create/update/list/delete split among siblings is self-evident, so the lack of exclusions is a minor gap.

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