generate_images

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

With no annotations, the description carries the full burden and does well: it discloses parallel multi-model execution, on-disk side effects (files written to out_dir), that results are returned for human/model selection, and relative cost of the judge mode. It omits failure/partial-failure behavior and permission or rate-limit considerations, keeping it out of the top band.

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 purpose and workflow are front-loaded in the first sentence, and the inline enumeration of review modes is dense but earns its space. The quoted mode syntax is slightly awkward to parse but no sentence is redundant.

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 10-parameter tool with no annotations and no output schema, the description covers the essential lifecycle: generation, persistence, return-for-review, and the manual copy step. Remaining gaps (what the return payload looks like per mode, error handling when a model fails) are modest but real.

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 coverage is 80%, so the baseline is 3, but the description adds real value by explaining the three 'review' enum values (paths/judge/inline) and their implications, which the schema does not document. It also clarifies the 'models' default (all of OAC_IMAGE_MODELS) and the out_dir default. The size/quality/background knobs are left to the schema, which is acceptable given the high coverage.

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 states a specific verb and resource ('Generate images') plus the distinctive mechanism: it fans out across every configured model in parallel, saves candidates to disk, and returns them for selection. This is far more informative than a tautological restatement and lets an agent understand the orchestration behavior immediately.

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?

It gives explicit mode-selection guidance ('paths' default, 'judge' is cheapest, 'inline' embeds images) and a clear post-step ('Copy the winner into the project yourself afterwards'). It stops short of stating when to prefer this tool over the unrelated siblings (web_search/web_fetch), but for a specialized generator that omission is minor.

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