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

Annotations already signal readOnly, idempotent, and non-destructive behavior, so the description doesn't need to restate those. It goes beyond by disclosing the specific payload components (IIIF 3 service, pixel dimensions, full-size JPEG, configurable scaled JPEG, thumbnail, rights statement), the graceful behavior when no image exists, and the keyless access requirement. This is valuable context annotations cannot provide.

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 compact yet informationally dense: two sentences plus a one-line example. It front-loads the core purpose, then enumerates outputs, then exceptions and access constraints, with no redundant phrases or restatements of schema content.

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 only two simple parameters and no output schema, the description carries the full burden of explaining return values. It enumerates every category of returned URL/content, covers the no-image edge case, notes access requirements, and gives a usage example. Nothing an agent needs to invoke it correctly is missing.

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 both parameters are already documented. The description adds meaning by connecting 'width' to the 'scaled JPEG' output and providing a concrete example ({id: '200107928', width: 1200}) that demonstrates realistic values. This slightly exceeds the baseline for full schema coverage.

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 identifies a specific resource ('one Rijksmuseum object') and a concrete deliverable (image URLs, including IIIF service, multiple JPEG sizes, dimensions, thumbnail, rights statement). It clearly distinguishes this from the similarly named rijks_search and rijks_object siblings by narrowing scope to a single object's image resources.

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 phrase 'Image URLs for one Rijksmuseum object' makes the applicability explicit, and the provided example shows exactly how to invoke the tool. It does not explicitly name alternatives or exclusion conditions, but the single-object scope and the mention of 'no published image' behavior give solid context for when this tool is appropriate.

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