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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description adds real behavioral context: what each view reveals, that 'status' returns output file URLs, and that wait.phase distinguishes queued (GPU waiting, jobs ahead) from loading_model/starting/generating/finishing. It stops short of error/auth or pagination behavior, keeping it at a 4.

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 front-loaded paragraph: 'Read a flow' first, then the view menu. Every clause earns its place, though the nested wait.phase enumeration makes it dense and slightly harder to scan than an itemized breakdown would be.

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?

There is no output schema, so the description carries the return-value burden and does so by characterizing what each view returns (raw nodes/connections/parameters, plain-language summary, execution state and file URLs, pre-run problems). It is complete for an agent deciding which view to request.

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 baseline is 3, but the description goes well beyond the schema's terse 'One of: detail (default), summary, status, validation' by explaining the payload each view returns and the diagnostic purpose of each. The flow_id meaning is self-evident from the schema.

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 ('Read a flow') and immediately scopes it with a view selector. It is clearly distinct from mutation siblings like edit_flow/delete_flow, but it never names a sibling explicitly to route the agent (e.g., list_flows for enumeration), so it falls just short of a 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?

Gives explicit when-to-use guidance per view: 'detail' to discover node IDs, 'summary' for plain-language description, 'status' for execution state, 'validation' for pre-run problems. This is strong routing guidance, but it offers no exclusions or comparison against alternatives such as list_flows or preview_flow.

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