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

Annotations only indicate readOnlyHint=false and destructiveHint=false, so the description adds meaningful behavior: transactional writes, exact output files, read-back proofs, and preservation of unrelated files. It does not contradict any annotation and gives an agent useful operational expectations beyond the structured fields.

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?

The description is compact and information-dense: three sentences cover the action, outputs, return proofs, and file-preservation behavior with no filler. The most important scoping statement ('Read one Figma frame') is front-loaded.

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 tool with no output schema and non-trivial write behavior, the description explains what is written, what is returned, and that unrelated files are preserved. Minor gaps remain around the exact meaning of 'transactionally' and failure/error behavior, but the description is largely sufficient for invoking the tool correctly.

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 the parameters are already fully documented in the schema. The description introduces no parameter-specific semantics beyond referencing the output directory context, which is acceptable given the schema already carries the burden.

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-resource pair ('Read one Figma frame') and exactly what artifacts it writes (frame.png, node.json, fills.json), which clearly distinguishes it from the sibling list_frames. It also states what the tool returns, removing ambiguity about its scope.

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 'Read one Figma frame' implies a targeted fetch operation as opposed to listing frames, and the mention of writing a local bundle gives context. However, it never explicitly says when to prefer this tool over list_frames or when not to use it, so the usage guidance is only implied.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the description correctly does not restate safety. It adds genuinely useful context by naming the required file_content:read permission and the concrete return payload, including nullable dimensions, metadata, completeness, request ID, and rate-limit proof. No contradiction with 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?

Two sentences with no fluff: the core action is front-loaded, followed by a compact list of return fields and the required permission. Every sentence earns its place.

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 simple two-parameter read-only list tool, the description covers the action, return values, and authentication requirement. The absence of an output schema is partially mitigated by enumerating return categories, though details on formatting or pagination are omitted.

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 both query and file_key are already sufficiently documented in the input schema. The description mentions filtering at a high level but adds no syntax or behavioral details beyond what the schema provides, so it stays at the baseline.

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 ('List'), a clear resource ('top-level FRAME nodes in a Figma file'), and the optional filtering behavior. It effectively distinguishes from the sibling fetch_frame by focusing on all top-level frames rather than a single frame.

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 makes it clear this tool is meant for enumerating or filtering top-level frames, which implies when it should be used. However, it never names the sibling fetch_frame or states when to prefer that alternative, so the usage guidance remains implicit rather than explicit.

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