fetch_frame

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

The annotation readOnlyHint=true is directly contradicted by the description's statement that the tool 'transactionally write[s] frame.png, node.json, and ... fills.json' under the output directory. While the description usefully discloses the file write behavior, the existence of the files, and the preservation of unrelated files, the contradiction forces a score of 1 per the rubric. The annotations also present a conflicting pair (readOnlyHint true + destructiveHint true), increasing confusion.

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 two sentences and every clause contributes: the first sentence states the core action and file outputs; the second lists return proofs and the preservation guarantee. Information is front-loaded and there is no redundant wording.

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?

Without an output schema, the description compensates by listing return proofs (upstream request proof, local size, SHA-256, PNG structure/dimensions, JSON read-back proof). It also notes that unrelated files are preserved, which signals the risk to the three named files. Gaps remain (e.g., no error behavior, no mention of whether out_dir is created, no guidance on obtaining node_id), but the core invocation context is covered well enough for a 4.

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 baseline is 3. The description references the output directory but does not add extra semantic detail for file_key, node_id, scale, or out_dir beyond what the schema already provides. No compensation is needed, so 3 is appropriate.

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 specifies a concrete action: read one Figma frame and write three named files (frame.png, node.json, fills.json) with normalized data. It clearly identifies the resource (a single frame) and expected outputs. However, it does not explicitly differentiate from the sibling list_frames, so it stops short of a full 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?

The description offers no guidance on when to use this tool versus list_frames, nor any prerequisites such as obtaining a node_id via list_frames or ensuring the output directory exists. There are no exclusions or alternative routing hints, leaving the agent to infer usage from the name.

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