Re-render an image against a new prompt

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

Annotations already declare the mutation profile (readOnly=false, idempotent=false, destructive=false, openWorld=true), so the safety burden is lifted. The description adds a genuinely useful non-annotation trait, GPU cost, but does not disclose whether prior renders are preserved or how the confirmation gate interacts with cost—though the confirm parameter covers that in the schema.

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 structural behavior before the usage rationale and cost note. The 'rolling a new grid and hoping' clause is slightly colloquial but earns its place as a routing cue; otherwise there is no waste.

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 7-parameter mutation tool with no output schema, the description covers the essentials: what it preserves, what it changes, and that it costs GPU time. It stops short of describing what comes back (a new job id?) or long-run queue behavior for the relax speed, minor gaps given annotations carry the safety profile.

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 every parameter including the enum'd speed, index bounds, and confirm gate is already fully documented. The description adds no parameter-level syntax or format detail beyond that, which is the expected baseline when the schema does the 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?

The description gives a specific verb+resource ('re-render an image') plus the key invariant ('keep an image's composition'), which clearly scopes it as a variation tool. It does not name the closest siblings (vary_image, rerun_job, upscale_image), so an agent must infer differentiation from the phrasing 'rather than rolling a new grid' alone.

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 states a clear use case ('change the subject or the styling of something you already like') and implicitly contrasts it with fresh generation, which is the right decision boundary. However, it never explicitly names the alternative tool to call when you do NOT like the composition, leaving sibling routing to inference.

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