list_images

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

With no annotations provided, the description must disclose behavioral traits. It mentions 'stable ordering', which hints at deterministic pagination, and implies reading images. However, it does not disclose that the tool is read-only, how pagination works (offset/max_results), or any edge cases like empty datasets. The schema provides parameter details, but the description adds only minimal behavioral context.

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 a single sentence that front-loads the main action ('discover dataset images') and immediately specifies two key features. Every word contributes; there is no filler. It is efficient and easily scannable for an AI agent.

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?

Given the tool has 6 parameters (1 required) and a known output schema, the description covers the core functionality (list with filter and ordering) but omits mention of pagination or the output format. Since an output schema exists, return-value details are not required. The description is reasonably complete for an agent that can infer pagination from the parameters. A few more words on usage context would earn a 5.

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 each parameter already has a description. The overall description adds the term 'stable ordering', which clarifies the intent of the order_by and random_seed parameters. This is a slight addition beyond the schema. Parameters like dataset_id, offset, and max_results are not elaborated further; the schema suffices. Baseline 3 is appropriate.

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 uses the verb 'discover' to indicate listing, and clearly identifies the resource as 'dataset images'. It mentions two key features: status filtering and stable ordering, which are accurate. However, it does not explicitly differentiate from sibling tools like list_annotations or list_categories, leaving the agent to infer the resource type from the tool name.

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?

No guidance is provided on when to use this tool versus alternatives. The description does not state prerequisites, when not to use it (e.g., for annotation listing), or compare with siblings. The context signals show sibling tools like list_annotations and preview_image, but the description offers no differentiation.

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