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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description reinforces this with 'Mutates nothing. Nothing is sent to real users and no state is written.' It goes further by explaining determinism, AST compilation, and the important caveat that a summary of 'none' means a green verdict proves nothing. This adds significant behavioral context beyond the annotations with no contradiction.

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 dense but well-structured. It leads with the core purpose, then usage, then smoke-layer details, then scenarios, then return format and a critical caveat. Every sentence earns its place; no filler. It is appropriately sized for the tool's complexity without being bloated.

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?

Given there is no output schema, the description fully compensates by stating the return object { passed, smoke, scenarios, summary } and explaining the meaning of 'passed' and the 'none' caveat. It also covers error handling (malformed steps are dropped), linked-flow behavior, and scenario constraints (at most 6, 15 steps). 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 description coverage is 100%, so the baseline is 3. The description does not add new meaning to parameters beyond what the schema already provides—e.g., flowIds' idRemap source and applicationId's default behavior are already in the schema. The description's extra context (like 'normally the flows apply_actions just created or changed') is redundant with schema text. It adds no distinct value here.

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: 'Runs deterministic behavioural tests against flows'. It clearly distinguishes itself from siblings by stating it runs after apply_actions, and explicitly contrasts the smoke layer with scenario-based assertions, so an agent can tell it apart from apply_actions and validate_actions without opening their schemas.

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 says 'Call after apply_actions to verify a build' and later 'patch with apply_actions, re-run', which gives a clear workflow. It also explains when to pass scenarios ('the only way to assert exact texts or exact stored values'), but does not explicitly name alternatives or state when NOT to use it. The guidance is strong but not exhaustive.

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