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

With no annotations provided, the description carries the full behavioral burden, and it does disclose the key trait: 'Read-only.' That covers the safety profile adequately for a simple list operation. It says nothing about pagination, error behavior, or what a 'flow starting point' actually contains in the response, so the disclosure is minimal rather than rich.

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 short sentences, front-loaded with the resource and its scope, with the read-only trait appended where it is easy to find. No filler or redundancy.

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 one-parameter, read-only list tool with no output schema and no annotations, the description states enough to invoke it safely. It is still thin on how the returned flows relate to the data from get_prototype_graph, which an agent choosing between the two would want.

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?

There is a single parameter with 100% schema description coverage, and the schema already documents the file key format including the design URL alternative. The description adds no parameter-level detail beyond what the schema provides, so the baseline of 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?

The description gives a specific verb and resource: 'List explicit Figma prototype flow starting points and their pages.' An agent knows exactly what data comes back. It does not, however, distinguish itself from the sibling tools get_screen_interactions and get_prototype_graph, which overlap in the prototype-graph space.

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?

There is no statement of when to use this versus get_prototype_graph or get_screen_interactions, and no prerequisite or scope guidance. The only usage signal is the phrase 'starting points,' which implies a narrower scope than the siblings but is never made explicit.

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?

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.

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

No annotations are provided, so the description carries the behavioral burden. 'No AI inference' is a genuinely useful disclosure that results are raw extraction rather than interpreted, but it omits read-only status (implied by 'get'), auth requirements, error behavior, or any pagination/limits.

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 short sentences, front-loaded with what is returned and immediately qualified by the no-inference clause. No wasted words.

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 two-param read tool with no output schema and no annotations, the description enumerates the returned content (triggers, actions, conditions, resolved destinations) and clarifies fidelity, which is close to sufficient. Missing safety/auth notes keep it from a 5.

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% for both required params (fileKey accepts file key or URL, screenNodeId format given), so the schema already does this work. The description adds nothing about the parameters, which is acceptable at full coverage — baseline 3.

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 (get) and resource (triggers, actions, conditions, resolved destinations for one Figma screen). The scope 'one screen' hints at the narrower grain versus the sibling get_prototype_flows/graph, but it never names or contrasts them explicitly.

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?

There is no statement of when to pick this over get_prototype_flows or get_prototype_graph, and no prerequisites or exclusions. The only guidance-ish signal is 'No AI inference', which describes output fidelity rather than selection context.

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