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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the trailing 'Read-only' is largely redundant. The genuinely additive part is 'Does not add sample screenshots', which reassures the agent this call has no side effect on project content, plus a brief note on what comes back (paths, preview metadata). It does not cover ordering, empty-state behavior, or pagination.

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 short sentences, front-loaded with what is listed and followed by the exclusion and the safety note. No filler, though 'Read-only' duplicates the annotation and could have been spent on the projectId semantics instead.

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 structure need not be described, and annotations carry the safety profile. The remaining gap is sibling disambiguation against list_screenshots and view_screenshot, which matters given the crowded list_* namespace.

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?

The single parameter projectId has zero schema description coverage and is not mentioned in the description at all. Its meaning is fairly self-evident from the name and the tool is scoped to one project, but the description does nothing to compensate for the missing schema documentation (e.g. that all returned paths are relative to that project).

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 verb and resource ('Lists real uploaded app screenshots') and adds scope detail ('across device types and platforms', 'project-relative paths'). It hints at a distinction from other screenshot sources by emphasizing 'real uploaded' and 'Does not add sample screenshots', though it never names the sibling list_screenshots, so the boundary is inferable rather than explicit.

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 'suitable as generation inputs' implies when this list is the right one to call, and 'Does not add sample screenshots' acts as a negative qualifier. But there is no explicit when-to-use statement or named alternative (list_screenshots, list_mockup_media), so an agent must infer the routing.

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