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

Annotations already declare idempotentHint=true and destructiveHint=true, but the description adds real context beyond them: no charge and no notification on save, a hard cap of 200 per owner, and that no watch is created. It does not explain why destructiveHint is set or what data could be affected, so it stops short of full transparency.

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, front-loaded with the core action and quota. Minor redundancy: 'nem notificação' in sentence one is needlessly repeated as 'não cria vigia nem notificação' in sentence two, though every statement still earns its place.

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 one-parameter, no-output-schema tool with annotations present, the description covers quota, absence of charge/notification, and the ID-only input contract. The only gap is not addressing the destructiveHint annotation, which an agent might want explained.

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% with a single documented parameter, so the baseline is 3. The sentence 'O cliente fornece somente o ID; o retrato vem do acervo' reinforces that only the id is needed and the payload is pulled from the archive, but this largely restates what the schema already says.

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?

Names a specific verb and resource ('Salva a compra') and immediately scopes it with what it does NOT do ('sem cobrança nem notificação', 'não cria vigia'), which distinguishes it from alert-related siblings like vigiar_compra and criar_alerta. An agent can identify the operation without opening the schema.

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 its niche by clarifying that saving does not create a watch or notification, which helps separate it from vigiar_compra, and it states a quota ('até 200 por dono'). However it never explicitly names an alternative tool or states when to prefer salvar over watch/alert flows, so usage is only implied.

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