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

The description adds 'criada se não existir' (created if doesn't exist), a side effect beyond what annotations disclose. Annotations state readOnlyHint false (mutation) and destructiveHint false, which are consistent. However, it does not mention potential errors, permission requirements, or effects on existing labels. It adds some context (bulk support) but not enough to be higher.

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 exceptionally concise: two short sentences, with the primary action front-loaded and bulk support mentioned second. No filler words or 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?

Given the tool has 5 parameters, no output schema, and annotations that are all false hints, the description should provide more context. It only covers label and note_ids, omitting unsafe and account. No mention of return values or error handling. For a tool with multiple knobs, this is incomplete.

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?

With 0% schema coverage, the description must explain parameters. It does clarify 'label' is by name and 'note_ids' enables bulk, but it does not explain 'unsafe' or 'account', and 'note_id' is not explicitly described beyond being required. The incomplete parameter coverage leaves significant gaps for a 5-parameter tool.

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 clearly states the action: 'Anexa uma label... a uma nota' (adds a label to a note), including that the label is created if it does not exist. This verb-resource pair is specific and distinguishes it from siblings like keep_create_label (creates label standalone) and keep_remove_label_from_note (removes label).

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 usage (adding labels to notes) and mentions bulk support with note_ids, but does not explicitly state when to use this over alternatives. It does not provide exclusions or context like 'use if you need to add a label, use keep_create_label if you only need to create it.' The bulk mention gives a hint but no explicit when/why.

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