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

Annotations already declare this is a non-destructive, idempotent write, so the description is not obligated to restate safety. It still adds real behavioral context: the job must be owned and completed, saving does not generate or charge, and the result is either a new identity or a look depending on the recipe. What it omits is what the call returns (e.g., a saved-character identifier) and any failure modes for an invalid jobId.

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 definition is front-loaded with the core action and input sourcing, then follows with prerequisites and cost behavior. The 'Generic image generation does not create a saveable Character Builder recipe' sentence partially repeats the Builder-workspace recipe point, which is the only real redundancy in an otherwise tight five-sentence block.

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?

For a three-parameter mutation with no output schema and zero schema description coverage, the description covers prerequisites, provenance of inputs, cost behavior, and result semantics well. The remaining gaps are the unexplained 'name' parameter and the absence of any statement about what a successful save returns.

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 carries the burden; it explains jobId as belonging to an owned completed Builder job and imageUrl as the exact original image, which is meaningful. However, the required 'name' parameter (maxLength 80) is never mentioned, leaving one of three required inputs entirely undocumented.

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 opens with a specific verb and resource: 'Save the exact original image of an owned completed Character Builder job,' and scopes the inputs (jobId, original imageUrl). It also clarifies the downstream effect (new identity vs. look depending on the Builder recipe) and distinguishes itself from generic image generation. It does not explicitly name a sibling tool, which keeps it short of a 5.

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?

'Save only on request' is an explicit when-to-use constraint, and 'Use the Builder workspace to author the recipe' plus 'Generic image generation does not create a saveable Character Builder recipe' states the prerequisite condition that makes a save valid. There are no named alternatives (e.g., in contrast to prepare_generation or select_saved_character), so guidance is clear but not fully comparative.

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