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

Annotations already cover the write/idempotent/non-destructive/closed-world profile. The description adds genuinely new behavior: no credit cost ('Free'), changes are recorded in version history (hence recoverable), URLs must echo prior results, and the change is invisible publicly until published. It does not say what happens if a URL is rejected or what the response contains, keeping 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?

Very short and front-loaded: the core action and its inputs come first, constraints follow. The telegraphic fragments ('Free.', 'Recorded in version history.') carry real information rather than padding, though the staccato style slightly costs readability.

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 mutation tool with full annotation coverage and no output schema, this covers the essentials: valid input sources, cost, reversibility via version history, and the publish requirement. Not fully complete because it omits failure behavior for invalid URLs and what the caller receives on success.

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 site_id, variation_id, user_goal and the replacements fields are already documented. The description only reinforces one nested field (concept_library_id) and the notion that original_url/new_url must be echoed from earlier results — useful but marginal over the schema, so the 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?

States a specific verb and resource — replace images on a design with user-chosen ones — and immediately disambiguates itself from the candidate-producing siblings (regenerate_images, explore_image_concepts). An agent knows this is the 'commit the choice' step, not the generation step.

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?

Explicitly names the two upstream tools that produce valid input and the exact flag needed (apply: false, send concept_library_id), plus the condition that publishing is required for visitors to see the change. Missing only an explicit statement of when *not* to call (e.g. before any candidates exist), which is implied by the provenance rule.

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