plan_validate

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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so the safety profile is covered; the description adds real substance by enumerating the three verification dimensions and disclosing that original folders need not stay connected after snapshots. It stops short of saying what happens on a failed verification (exception vs. report).

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?

A single dense sentence with the core verification targets front-loaded and the folder-disconnection caveat trailing as a secondary clause. No wasted words, though the semicolon-joined caveat slightly obscures the primary action.

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?

Read-only annotations and a fully described nested schema carry most of the load, but with no output schema the description never says what a verification returns — a pass/fail boolean, a list of violations, or an error — which matters for an agent deciding how to react to the result.

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?

Only one parameter, and the schema documents it to 100% coverage including the nested {id, revision} artifact reference and project_id format. The description adds no parameter-level meaning beyond that, so baseline 3 applies.

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 (Verify) bound to three concrete checks: immutable plan input hashes, runtime compatibility, and resource preflight. The object under test ('plan') separates it from the many sibling *_validate tools (dataset_validate, workflow_validate, simulation_validate), though it never names or contrasts those siblings explicitly.

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?

'Preflight' implies the check runs before execution, and the schema's 'calculation_plan artifact ... with status READY' hints at the precondition, but the description never states when to call this versus calculation_run or the other validators, nor what to do on failure. Usage is inferable rather than stated.

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