aya_evidencia_registrar

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

With no annotations present, the description must carry the full behavioral disclosure. It does disclose the key trait 'append-only' and warns about gate violations, which is useful. But it does not mention permissions, error behavior, irreversibility beyond append-only, or what happens on duplicate registrations.

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 short sentences, front-loaded with the core action and the append-only trait, followed by a meaningful warning. Every word earns its place; no filler or repetition.

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 five required parameters, no annotations, and no output schema, the description is incomplete. It conveys the operation and a key constraint but leaves the agent guessing about parameter meaning, return value, failure modes, and how this tool interacts with the broader evidence workflow.

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 of parameters in the description is effectively 0% — it says nothing about 'tarefa', 'tipo', 'descricao', 'aprovado', 'resultado', or 'comando'. The schema itself defines types and the enum for 'tipo', but the required fields 'descricao' and 'resultado' are not even listed as properties in the given schema snippet, and the description provides no compensation.

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 ('Registra evidencia') and the resource (evidence), with the added trait 'append-only' distinguishing it from modification or deletion tools. The second sentence adds context about the inherited gate, reinforcing what this tool is for, though it does not explicitly differentiate it from sibling evidence tools.

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 gate warning ('Decarar pronto sem evidencia observada viola o gate herdado do Agents') implies that this tool should be used before declaring a task as ready, and that it is required to avoid violating the gate. However, it does not explicitly state when to use this tool versus alternatives like aya_evidencia_listar or aya_evidencia_validar_tarefa.

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