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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the trailing "Read-only." adds nothing. The genuinely additive detail is the ordering (newest first) and the fact that active/ready/has_content status flags appear in results, but there is no mention of pagination, result caps, or what an empty list means.

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 front-loaded sentence with no waste: scope, ordering and returned state are packed in, and the read-only note is short. Nothing needs trimming or reordering.

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?

An output schema exists, so return values need not be explained, and read-only safety is covered by annotations. However, for a 3-parameter list tool with an alias pair (projectId/generationId) the description omits that the project selector is optional and how the two identifiers relate, which is the main thing an agent could get wrong.

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?

At 67% schema coverage the baseline is 3. The description only gestures at contentType ("one project content type") and never mentions projectId/generationId or their alias relationship, leaving the schema's own descriptions to do all the work on the two UUID parameters.

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 names a specific verb and resource ("Lists variants") and adds scope ("for one project content type"), ordering ("newest first") and the status flags returned. It does not explicitly distinguish itself from siblings like get_project or list_screenshots, which keeps it from a 5.

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?

Usage is only implied by the phrase "for one project content type" – there is no statement of when to call this versus get_project or list_screenshots, no prerequisites, and no note that projectId/generationId is optional while contentType is required. An agent can infer the intent but is given no routing guidance.

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