Vocabulary

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

With no annotations, the description carries the whole burden. It discloses the return shape per action ('list → [{id, name}]', 'create → {id, name}', 'delete → {status: deleted}') and the tags-vs-labels distinction, which is genuinely useful. It omits permission/auth requirements and, importantly, does not say what deleting a label does to items already carrying it — a real gap for a destructive action.

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?

Labelled sections (Use quando / Retorna / Exemplo / Notas) front-load the trigger and pack parameters, returns, and an example into four short blocks. Dense and readable with very little filler; slightly compressed syntax but nothing wasted.

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 5-parameter, no-required, multi-action tool with 0% schema coverage and no output schema, the description supplies the missing action model and per-action return shapes. Only 'connection_id' and the exact effect of delete on existing item tags are unaccounted for.

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 0%, so the description must compensate, and it largely does: it defines the allowed values of kind ('tags | labels'), the action set and the argument each action takes ('create (name)', 'delete (id)'). Only 'connection_id' is left unexplained, and the enums remain informal rather than schema-enforced.

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 opening line names the resource precisely ('tags (livres)' vs 'labels (lista controlada)') and the actions surface in the example and notes (list/create/delete). An agent can tell it deals with the tag/label vocabulary rather than items or structures. It stops short of an explicit verb+resource sentence up front and does not name the sibling it is distinct from.

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 'Use quando' line gives a concrete trigger (reuse existing tags before creating variants; manage labels), and the closing note routes the agent to item_save for the overlapping case of creating tags on an item. Clear context, but no explicit when-not-to-use beyond that one overlap.

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