Monitorar OAB, parte ou processo no DJEN

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

Annotations already declare readOnlyHint=false, idempotentHint=false and openWorldHint=true, so the write/non-idempotent nature is covered. The description adds two things beyond that: the API key requirement and the fact that delivery is push-based via webhook on every new publication, which tells the agent this is a persistent, recurring side effect. It omits where the webhook target comes from, since no webhook parameter exists in the schema.

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 compact segments: the prerequisite first, then a single sentence naming the resource and its trigger. Nothing is redundant and the most decision-relevant constraint (advanced/API key) is front-loaded.

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 state-creating tool with no output schema, the description never says what comes back (a monitor identifier, status) or how an existing monitor is inspected or removed. Combined with the unexplained webhook destination, an agent can invoke it correctly but cannot reason about the full lifecycle of the object it creates.

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 100%, with 'alvo', 'tipo' (enum) and 'rotulo' each documented in the schema, so the baseline of 3 applies. The description only restates the target domain ('OAB, parte ou processo'), adding no syntax or defaulting detail beyond what the schema already says about deducing 'tipo' from 'alvo'.

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?

Specific verb plus resource ('Cria um monitor') and a clear scope ('publicação nova de uma OAB, parte ou processo' no DJEN). An agent understands exactly what is created and what it observes. It does not explicitly contrast with the search sibling (buscar_publicacoes_djen), so it stops short of full sibling differentiation.

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 bracketed '[Avançado: exige BITBUSCA_API_KEY]' flags a prerequisite and points at the activation path (como_ativar_avancado), which is real guidance. However, it never states when to prefer this over a one-off search of publications, nor when not to use it (e.g. duplicates, monitoring already exists). Usage is implied rather than prescribed.

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