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

Annotations already carry readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds value beyond that: the `images:manage` auth scope requirement, the GET /manage-images mapping, the note that billing and rate limits match the underlying HTTP API, and the signed-preview-URL return behavior. There is no contradiction with the read-only annotations.

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?

Five short, front-loaded segments: purpose, return behavior, auth scope, API mapping, and an anti-hallucination guardrail. Every sentence earns its place, and the closing instruction 'Do not invent other paths' is a high-value, low-cost addition that keeps agents from fabricating alternative endpoints.

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?

For a one-optional-parameter read-only list tool with rich annotations and no output schema, the description is sufficient. It states the resource, scope, return value (signed preview URLs), auth requirement, and HTTP equivalence. An agent has everything needed to invoke it correctly; response-shape or pagination details are not critical for an 'all images for the current app' read operation.

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%: the single optional x_app_id parameter is fully documented in the schema as an override for the X-App-Id header, defaulting to the MCP connection header. The description contributes no additional parameter guidance, so the baseline of 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?

The description opens with the imperative 'List images' then specifies the resource (images), the scope ('for the current app'), and the return payload ('including signed preview URLs'). It also maps to GET /manage-images, and among the sibling tools the only image-related operations are uploadImage, deleteImage, and getImageUsage, so this listing tool is clearly distinguishable.

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 gives implied usage context: it is the way to fetch all images for the current app, and it warns 'Do not invent other paths' and to expect the same API, billing, and rate limits. However, it never names an alternative or an exclusion — for example, it does not mention getImageUsage for image consumption analytics — so tool-selection guidance among siblings is left to inference.

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