List registered images

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

With no annotations, the description carries full responsibility for disclosing side effects. It explicitly states 'Read-only; doesn't consume credits,' which addresses the two most important behavioral concerns: no mutation and no resource cost. It does not mention pagination behavior or sorting, but schema parameters cover page/page_size, and for a simple list this is adequate transparency.

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?

The description is two sentences, front-loaded with the primary verb and resource, then follows with a useful filtering example and a critical safety note. Every sentence earns its place with no redundant or vague wording.

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?

The description is complete for a simple list tool: it states what is returned (key, url, updated_at), the scope (current project), and a filter mechanism. It does not have an output schema, but the return fields are explicit in the description. It lacks details on sorting or full pagination behavior, but given the simplicity and schema coverage, the description provides enough context for correct invocation.

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 the baseline is 3. The description adds a slightly richer example for `prefix`, showing that 'hero.' returns keys like hero.background and hero.foreground, but this is incremental over the schema. The other parameters (page, page_size) are already fully described in the schema and not re-explained in the description.

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 clearly states the tool's purpose: 'List image keys registered for the current project (key, url, updated_at).' It uses a specific verb ('List') and resource ('image keys') with an explicit scope ('current project') and return fields. It is easily distinguished from sibling tools like register_image, replace_image, and delete_image, which imply mutation or singular access.

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 description provides clear usage context: it is read-only, does not consume credits, and supports an optional `prefix` filter with a concrete example ('hero.' returns hero.background, hero.foreground). While it does not explicitly name alternative tools for single-image retrieval or list other scopes, the context is sufficient for an agent to know when listing images is appropriate and that it is safe to call.

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