grok_generate_image

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

With no annotations, the description carries the full burden and does so: it discloses that a missing page control in quality mode yields a warning rather than a failure, that files are never overwritten, that n=3/4 costs two submissions, and where files land. It also enumerates the return keys, so the agent knows what success and partial success look like.

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?

Purpose and quota constraint are front-loaded, then parameters are covered in a terse, scannable per-parameter list. For a 10-parameter tool with no schema descriptions, every line carries information; nothing is padding.

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?

No output schema exists, and the description compensates by listing the return keys and the optional sizes/warning fields. Combined with the quota, overwrite, and default-behavior notes, an agent can call this correctly; only timeout_s semantics and explicit error (as opposed to warning) behavior are left 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 coverage is 0% for 10 parameters, so the description must compensate, and it explains most of them: aspect enum values, n range and its submission cost, mode values and failure semantics, max_side, size (with an explicit precedence rule over max_side), keep_original, and out_dir resolution. Gaps remain for timeout_s (only covered by the generic "configured defaults" remark) and name, which is explained only obliquely through the file-naming pattern.

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 first sentence names a specific verb and resource ("Generate images with Grok Imagine") plus the execution mechanism (user's logged-in Chrome, no API key), which is far more than a restatement of the name. It implicitly separates itself from grok_generate_video by naming the medium, but never explicitly routes the agent away from siblings such as grok_batch.

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 concrete prerequisites and guardrails: quota is drawn from the user's own Grok plan, over-limit jobs are refused, and the agent is pointed at grok_usage() and grok_settings for limits and defaults. It stops short of stating when to prefer grok_batch or what to do on refusal (retry later vs. reduce n).

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