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

Annotations cover the safety profile (readOnly=false, destructive=false, idempotent=true), so the bar is lower, yet the description adds genuinely non-structural facts: no content generation, no credit spend, no publishing, and that it saves an inactive draft. It does not describe the draft's lifecycle or how to move it out of inactive, but the credit/publish disclosure is valuable context the annotations do not carry.

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 action and immediately followed by the negative constraints. Nothing is padded, though the phrasing is terse enough that it reads as a fragment list rather than a fully structured statement.

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 no explanation, and annotations plus the description cover the safety and side-effect profile adequately. The gap is the complex nested recipe schema at 0% coverage, which is neither documented in the schema nor compensated for in the description, leaving parameter usage under-specified.

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 3 parameters (including a deep nested 'recipe' object with dozens of undocumented fields), so the burden falls entirely on the description. It offers only the vague hint 'Only banner artwork' and says nothing about brandId, idempotencyKey, or any recipe field, leaving the parameters essentially unexplained.

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 ('Save an inactive review draft') and scopes it to 'Only banner artwork', which lets an agent distinguish it from the many generic prepare_* siblings. It stops short of naming an alternative tool explicitly, so it is clear but not fully differentiated by name.

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 line 'Does not generate content, spend credits or publish' implicitly tells the agent this is a draft-only step and not the generate_* or activate_* siblings, and 'the saved automation type must match this tool' is a real constraint. However, there is no explicit when-to-use trigger or named alternative, so usage is only implied.

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