Criar regra do inbox

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the write/non-destructive profile is covered structurally. The description adds genuinely new behavioral information: the confirmation gate (`confirm: true`) and the runtime effect that rules auto-categorize captured notifications. It omits other relevant behavior for an 8-parameter mutation — what happens on name collisions, how priority ranks competing rules, or the 10-condition cap.

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 with the core action front-loaded and the constraints trailing; nothing is padded. The only inefficiency is that the 'categoria ou pessoa' clause is both vague and in tension with the required-parameter list, costing a bit of precision.

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 that 7 of 8 parameters are required and schema coverage is 13%, the description leaves an agent with almost no understanding of the required payload beyond name-less category/person hints and the confirm flag. For a creation tool with nested condition objects and no output schema, this should do substantially more work.

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 only 13%, so the description must carry the burden and does not. It touches only categoryId/personId and confirm; name, priority, isActive, matchMode, and the conditions array (field/operator/value, including the numeric parsedAmount variant) are never explained. Worse, 'Informe ao menos categoria ou pessoa' suggests an either-or choice, while the schema marks both categoryId and personId as required, which can mislead an agent into omitting a key.

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 plus the effect: it creates a rule that automatically categorizes captured notifications. An agent can immediately tell this is a write tool about inbox categorization rules, distinct from list_inbox_rules/delete_inbox_rule. It stops short of naming which sibling to use for reviewing or removing rules, so it is not a 5.

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?

There is no when-to-use guidance and no reference to alternatives such as list_inbox_rules for inspecting existing rules or delete_inbox_rule. The sentences 'Informe ao menos categoria ou pessoa' and 'Exige `confirm: true`' are invocation prerequisites rather than guidance on when this tool is the right choice, so usage context is only weakly implied.

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