prepare_company_blueprint_native_proof

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

Annotations indicate idempotent=true, destructive=false, and readOnly=false, but the description only adds that data is 'derived from Spring custody' and lists proof outputs. It does not clarify whether the operation writes or prepares a persistent artifact, what happens on re-run, or what side effects exist despite the readOnly=false hint. The description does not contradict the annotations, but it provides little behavioral context beyond them.

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?

The description is a single sentence with no filler and front-loads the verb and object, so it is structurally concise. However, it is under-sized for a tool with five required parameters and heavy domain jargon, leaving important terms unexplained. It is terse in a way that sacrifices adequacy.

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?

With five required parameters, a rich set of blueprint lifecycle siblings, and an unexplained 'Spring custody' source, the one-sentence description is not complete enough. The existence of an output schema covers return values, but the description still omits prerequisites, what inputs the agent must assemble, and how this step fits into certification, deployment, or rollback flows.

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 0%, so the description must compensate, but it only obliquely echoes 'Loop' and 'rollback' without explaining any of the five required parameters. It does not define how company_ref, project_ref, blueprint_version_id, golden_loop_certification_record_ids, or rollback_shadow_intent_id relate to the derived proof. The parameter names provide surface-level hints, but the description adds almost no real semantic guidance.

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 names the action ('Derive ... proof') and a source ('Spring custody'), so it is not a tautology. However, it never defines 'native proof', 'Spring custody', or the specific proof types it lists, and it does not distinguish this tool from the many blueprint certification/deployment/rollback siblings. An agent gets a general sense of the action but not a precise, disambiguating purpose.

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 description gives no guidance on when to use this tool versus sibling tools like propose_company_blueprint_certification, finalize_company_blueprint_deployment, or request_company_blueprint_rollback. It also omits prerequisites, workflow ordering, or any conditions under which this preparation step should be called. The agent is left to infer placement in the lifecycle.

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