Datasets

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

With no annotations, the description carries the full burden, and 'Reads only' usefully declares the non-mutating nature. It also discloses the shape of returned data, but omits pagination/limit behavior, ordering, and what happens when a search or id matches nothing.

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?

A single dense sentence that front-loads the resource and separates the list mode from the detail mode with no wasted words. Nothing to trim.

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 correctly compensates by naming what a dataset record contains (files, captions, trained models) and flags read-only behavior. Missing only edge-case behavior (empty results, large lists) for a low-complexity two-parameter read tool.

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%: the schema already documents search as a case-insensitive substring and dataset_id as the single-record selector. The description restates these without adding syntax, format, or defaulting details, 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 resource (training datasets) and two clear modes: list or single-dataset-by-id, with the returned payload enumerated (files, captions, models). It distinguishes itself from ideogram_dataset_upload implicitly, but never names a sibling to route between them.

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?

'Optionally searched by name' and 'one dataset by id' imply when each mode applies, so usage is inferable. However, there is no explicit when-to-use vs alternatives (e.g., ideogram_dataset_upload for writing, ideogram_models for model listings) and no stated prerequisites.

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