validate_process_definition

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

Annotations already declare readOnly/idempotent/non-destructive, and the description reinforces this with 'SEM gravar nada (dry-run)'. It adds genuinely new behavior: the validation dimensions include cross-tenant ownership checks against referenced agents, approval policies and MCP servers, and it discloses the return shape (a list of errors with path and reason) despite no output schema existing. It does not say whether warnings vs hard errors are separated or whether validation is cheap/expensive, so it stops just short of the top.

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 tight sentences: what it does, what it verifies, what it returns, then the gating instruction placed last for emphasis. No filler, no restatement of the tool name, and the dry-run guarantee 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 single-parameter, non-mutating validator with no output schema, the description covers the dry-run guarantee, the validation scope, the return value, and the workflow position relative to publish. Nothing an agent needs to call it correctly is missing.

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%, so the baseline is 3, but the description adds meaning the schema does not: the spec carries references to agents, approval policies and MCP servers that are resolved against the caller's company, which tells the agent what content matters in the payload. It still does not describe the expected shape of spec beyond the schema's own hint.

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?

States a specific verb and resource (validate a process definition) plus the key qualifier 'SEM gravar nada (dry-run)', enumerates exactly what is checked (structure, engine rules, tenant ownership of referenced agents, approval policies, MCP servers) and says what it returns. The contrast with publish_process_definition makes it immediately distinguishable from the mutation sibling.

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?

'Rode sempre antes de publish_process_definition' gives an explicit, mandatory usage condition and names the alternative tool it gates. An agent does not need to infer when to reach for this tool versus publishing directly.

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