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

Goes meaningfully beyond the annotations by disclosing that the source is never overwritten, that outputs land in the output folder with a .json sidecar, and that paths plus small previews come back. It does not cover provider/credential constraints or cost/rate behaviour, but for a mutation tool flagged openWorld this is solid added context consistent with destructiveHint=false.

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?

Two sentences, zero filler: the action and examples come first, then the side-effect and return-format guarantees. Every clause carries information an agent would otherwise lack.

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?

With no output schema, the description usefully compensates by stating what is returned (paths and previews) and where files land. Minor gaps remain around the mask/provider restriction and any length or content limits on the prompt, but the specification is sufficient to invoke the tool correctly.

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 every one of the 8 parameters (including mask, references, transparent, out_name) already carries its own description; the description adds nothing about individual parameters. Baseline 3 applies since the schema does all the semantic work.

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+resource ('Change an existing image') and immediately grounds it with four concrete instruction examples, which makes the distinction from the generate_image/generate_set siblings apparent without naming them. An agent can tell this transforms an existing file rather than creating one from scratch.

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 framing 'an existing image' implicitly signals when to reach for this over generate_image, and the examples clarify the kind of prompt that works. But there is no explicit when-to-use/when-not statement and no reference to the siblings by name, so the routing decision is left to inference.

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

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

Annotations already flag a non-read-only, open-world, non-destructive operation. The description adds real value beyond them: it discloses that full-size PNGs plus a .json sidecar are written to the output folder and that paths with small previews are returned. It stops short of covering overwrite behavior when out_name collides, cost/latency of the external call, or failure modes.

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?

Two sentences, zero filler, and the core action is front-loaded before the side effects. Every clause adds information an agent needs.

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 six-parameter mutation tool with no output schema, the description adequately covers what is produced and where, so the agent knows the return shape. Remaining gaps are overwrite semantics for out_name and any cost/rate-limit caveats for the external generation call.

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 100%, so all six parameters are already documented with defaults and ranges. The description adds only output-side context ('one or more', paths, sidecar) and no syntax or semantics beyond the schema, which matches the baseline of 3 when the schema carries the burden.

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 gives a specific verb (generate) and resource (images) with the source constraint 'from a text prompt', which implicitly separates it from edit_image. It never names or contrasts the siblings edit_image or generate_set, so the boundary with generate_set ('one or more images') is left ambiguous.

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?

Usage is implied by 'from a text prompt' and the file-output behavior, but there is no explicit when-to-use, when-not-to-use, or routing to edit_image/generate_set. An agent must infer that this is the text-to-image entry point rather than a set generator or editor.

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

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

Annotations only declare the safety profile (not read-only, open-world, non-destructive), so the description usefully adds that each item produces its own file named after the item, all in one folder, and that paths and previews are returned. It stops short of stating overwrite/conflict behavior for an existing folder or any rate/cost limits, which matters given openWorldHint.

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 core purpose, followed by output layout and return values. No filler or repetition of schema details.

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?

It covers what the tool produces and what it returns (paths and previews), which compensates for the absent output schema on a 6-parameter tool. Gaps remain around folder collision behavior and whether style/items have any content restrictions, but nothing essential to invoking it is missing.

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 schema already documents style, items, size, folder, references, and transparent. The description contributes only the linkage that item names become file names and that everything lands in one folder — helpful but marginal, so baseline 3 applies.

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?

Specific verb (generate) plus resource (several images sharing one style), reinforced by concrete examples (icons, stickers, badges, portraits, story illustrations). It implicitly separates itself from generate_image by emphasizing 'several' and 'share one style,' but never names the sibling tools, so the differentiation is inferred rather than stated.

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 example list gives a reasonable sense of when a matched set is appropriate, but there is no explicit guidance on when to prefer generate_image for a single image or edit_image for modifying existing art. No prerequisites, exclusions, or cost/batching trade-offs are stated.

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