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

Annotations already establish read-only, idempotent, non-destructive behavior, but the description adds real value beyond them: the exact payload format and MIME type, the renderer/openUrl capability requirement, and that text links accompany the resource. It stops short of describing payload size or failure behavior when the renderer is unsupported, so not a full 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?

Three sentences, front-loaded with the hard usage gate, then the deliverable, then the routing alternative. No filler and nothing repeated from annotations or schema.

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 host-capability requirement and the contrast with get_realizations cover the highest-risk failure mode, which is the main thing an agent needs. However, with 11 loosely documented parameters and no output schema, an agent still has to infer which filters behave like the sibling tool and how to construct a valid A2UI request.

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?

With 11 parameters and only 45% schema description coverage, the description needs to carry weight, but it only mentions 'optional location' and 'no writes'. The other parameters (scope, service, object_type, area bounds, initial_state) get no semantic clarification beyond their schema text, leaving the coverage gap unfilled.

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 concrete verb and deliverable: returns self-contained A2UI v0.9.1 Basic Catalog messages as an application/a2ui+json embedded resource, plus text links. It also names what the search is based on ('same public realization search'), which lets an agent distinguish it from get_realizations without reading either schema.

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?

Explicit gating ('Use ONLY when an A2UI-capable host or the user explicitly requests A2UI'), an explicit alternative ('For normal gallery requests use get_realizations (MCP Apps)'), and the prerequisite for the alternative (renderer supporting this catalog and openUrl). Both the when and the when-not are stated.

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