create_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 disclose non-obvious traits: an authenticated web session is required, persistence differs by transport (stdio and local bridge write a file and return a path; direct hosted HTTP returns inline artifacts and never writes paths), and a session token enables follow-up edits. It omits side-effect details such as quota consumption on the underlying provider accounts, rate limits, or latency, which keeps it below a 5.

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 is front-loaded in the first sentence, and the remaining sentences each map to a distinct mode/parameter decision. A few clauses restate schema descriptions almost verbatim, which is minor redundancy rather than bloat.

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 five-parameter tool whose behavior changes with transport, the description covers the mode split, the persistence model, and the return shape (path vs. inline artifacts) even though no output schema exists. What remains unstated is failure behavior and the provider/failover mechanism, so it is strong but not fully complete.

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 100%, so the baseline is 3; the description goes further by explaining the interaction between parameters – `prompt` and `file` combine for an edit, `session` is the value returned by a prior call, and `path` only matters for the modes that persist locally. It does not explain `provider` selection or failover, which is left entirely to the schema text.

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 pair and resource ('Generate or edit an image') plus the channel ('via a logged-in web session'), so an agent knows exactly what the tool does. It also distinguishes its own sub-modes (new vs. edit vs. continue-session), and none of the siblings (browser, read, search, usage, deep_research) overlap with it.

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?

Gives explicit routing for each path: pass `prompt` for a new image, pass `file` in local stdio mode to edit, pass `session` to continue a ChatGPT image chat. It covers the conditions for using each parameter but never states a when-not-to-use case or what happens on failure, so it stops short of a 5.

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