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

Annotations already declare destructive=true, readOnly=false, and idempotent=true, so the safety profile is covered by structured data. The description adds genuinely new behavioral context: that the reviewed sample is invalidated as a side effect and that no generation or publishing is triggered, which tells the agent what state is destroyed.

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 short sentences, front-loaded with the core action and side effect, then constraints. No filler, though the 'Only original generated images' phrase is slightly elliptical for a first-time reader.

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?

An output schema exists, so return values need not be explained, and the destructive/no-generate behavior is disclosed. Still, for a mutation tool whose main payload is a deeply nested recipe with 0% field documentation, the description leaves key structural expectations unaddressed.

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% across 5 required parameters, including a large nested recipe object with dozens of undescribed fields. The description names only 'recipe' and adds no semantics for brandId, automationId, revision, or idempotencyKey, so it does not compensate for the coverage gap.

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 ('Replace this automation's recipe') plus a side effect ('invalidate its reviewed sample'), which is far more informative than a bare 'update'. The clauses 'Only original generated images' and 'the saved automation type must match this tool' differentiate it from the other update_*_automation siblings, though it never names a sibling directly.

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?

'Does not generate or publish' implicitly contrasts this tool with the generate_*_sample siblings, and 'the saved automation type must match this tool' gives a precondition. However, there is no explicit statement of when to choose this tool versus prepare_/activate_/resume_, nor any exclusion beyond the type match.

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