figma_list_screens

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

Annotations already declare readOnlyHint=false, openWorldHint=true, and non-idempotent, so the agent knows this is a state-changing, network-reaching call — but the description never explains what gets created on import, whether it's repeatable, or that it requires Figma connectivity. The dual-mode behavior is the single most important thing to disclose and it is left implicit.

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 short sentence with no wasted words, but the brevity is under-specification rather than economy — it front-loads two operations without disambiguating either. Room exists for the missing mode-selection logic without bloat.

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 6-parameter tool with zero required fields, no schema descriptions, no output schema, and two distinct behaviors, the description is far too thin. An agent would have to guess how to invoke it correctly and what a successful call returns or mutates.

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?

Six parameters with 0% schema description coverage, so the description carries the full burden and supplies almost nothing. 'Figma link' loosely gestures at the url parameter, but fileKey, nodeId, snapshotId, limit, and offset are entirely unexplained — including the critical question of which parameters are mutually exclusive between the list and import modes.

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 two distinct operations ('list reference screens' and 'import a Figma link'), so the verb/resource is present but the tool's actual identity is ambiguous — the name says list_screens while the description also performs an import, which overlaps with the sibling figma_import. An agent cannot tell from this text alone whether calling it with a url creates state or just resolves references.

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?

No guidance on when to choose this over figma_import, figma_list_snapshots, or figma_get_screenshot. The two operating modes (snapshotId-based listing vs url-based import) are implied only by the word 'or', with no statement of which argument selects which mode or what prerequisites (e.g. a connected Figma account) apply.

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