get_prototype_graph

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

No annotations are provided, so the description carries the full burden. It usefully discloses a real limitation ('does not infer missing links') and that results are provenance-aware, but says nothing about permissions, rate limits, or whether the graph is a snapshot. A meaningful but incomplete behavioral picture for an unannotated tool.

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?

One tightly packed sentence plus a short boundary clause, front-loaded with the verb and resource. Every clause earns its place: purpose, optional scoping, and the inference limitation.

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?

With no annotations and no output schema, the description still covers purpose, scoping, and the key non-inference guarantee. It is nearly complete for a read-only graph fetch, though it never hints at the shape of the returned graph (nodes/edges), which would help given the absent output schema.

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 coverage is 100%, so the schema already documents both parameters (fileKey accepts URL or key, startNodeId is a flow/screen node ID). The description adds the semantic that startNodeId restricts output to reachable nodes, which is a modest gain over the schema wording. Baseline 3 applies.

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: fetch explicit Figma prototype interactions and navigation as a graph, with the scope narrowed by the optional startNodeId. It does not name the siblings get_screen_interactions or get_prototype_flows, so the agent must infer the boundary from the 'explicit / does not infer' phrasing rather than being routed directly.

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 conditional 'optionally limit to nodes reachable from a flow/screen' implies when to pass startNodeId, but there is no explicit statement of when to prefer this over get_prototype_flows or get_screen_interactions. Usage is implied rather than stated.

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