publish_process_definition

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the safety frame is covered; the description adds real value on top by explaining version semantics (new version created, live instances unaffected) — which confirms the non-destructive, non-idempotent profile. It also discloses that the publish performs validation of structure, rules, and tenant ownership of referenced agents/policies/MCP servers, going beyond what annotations say. It stops short of describing the response or failure behavior.

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?

Front-loaded with the action and its version consequence, then the prerequisite, then the spec constraint. The parentheticals each carry information rather than restating the name, though the density of clauses makes it slightly heavy for a single-parameter tool.

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 tool whose `spec` is an untyped open object with no output schema, the description supplies the essential missing pieces: version handling, the validate-first requirement, tenant-scope validation of referenced resources, and what belongs inside the definition. Nothing an agent needs in order to call it correctly appears to be absent.

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% and the single `spec` parameter is an open object, so the schema itself conveys almost no structure. The description compensates by stating the definition must omit `version` (the platform computes the next one) and by hinting at the worker-recipe shape (`request` or `requests` + `choose_from`), which is meaning the schema cannot provide.

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+resource ('Publica uma definição de processo') and immediately clarifies the non-obvious semantic: it creates the NEXT version of the key, the current one becomes active for new openings, and live instances stay on their original version. This distinguishes it cleanly from list_process_definitions, get_process_definition, retire_process_definition and enable_process.

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?

Explicitly routes the agent to a prerequisite: run validate_process_definition before publishing, which is the key sequencing decision. It does not spell out exclusions (e.g. when to use retire_process_definition or publish_agent instead), so it falls short of full when/when-not guidance, but the practical context is clear.

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