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

Annotations already declare readOnlyHint, idempotentHint and non-destructive, so safety is covered. The description adds genuinely non-obvious context: results omit generated HTML, which explains why the payload is light. It does not mention pagination behavior, though the limit/offset params and output schema cover that.

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 sentences with zero filler, front-loaded with the primary purpose before the routing instructions. Each sentence earns its place by directing the agent to a specific follow-up tool.

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 value documentation is unnecessary. The description covers the metadata-only scope, the ID mapping for downstream calls, and when to prefer get_component, leaving nothing essential for correct invocation 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 description coverage is 100%, so projectId, limit and offset are already documented in the schema, making 3 the baseline. The description's ID guidance (screenId vs id) describes output item fields rather than the input parameters, so it adds little to input semantics.

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 ('List a project's screen names and active version numbers'), and clarifies that 'components' in the tool name are actually screens, which the title 'List screens' only hints at. It distinguishes itself from get_component by noting this returns metadata 'without generated HTML'.

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?

Explicitly routes the agent: pass screenId to design, pass id as componentId to get_component or screenshot, and a stated exclusion ('Use get_component only when you need a screen's code'). This is textbook when-to-use/when-not/alternative guidance.

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