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

Annotations already establish this is a read-only, idempotent, non-destructive operation. The description adds valuable context beyond annotations by explaining what each view returns: 'status' includes execution state and output file URLs, 'validation' lists specific issues like trashed, running, missing inputs, and disconnected nodes. This enriches the behavioral profile without contradicting any annotation.

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 a single, well-structured sentence that uses a clear pattern: 'Read a flow. Pick the view...' followed by four compactly defined options. Every clause adds useful information, with no filler or redundancy. The use of semicolons and em-dashes keeps it readable despite covering four distinct behaviors.

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?

Given the tool has no output schema, the description effectively explains what you will get for each view: raw nodes/connections/parameters for detail, plain-language summary, status with URLs, and validation with specific problem categories. This covers the full scope of the tool's functionality without needing to describe a separate return format. Sibling context (many flow operations) is adequately addressed by clarifying this is the read/retrieval tool.

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?

While the schema already describes both parameters (flow_id and view with enum values), the description adds substantial meaning by explaining what each view value produces and when to choose it. For example, 'detail' is for discovering node IDs, and 'summary' gives a plain-language description. This goes well beyond the raw schema description, which only lists the enum values.

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 opens with a specific verb+resource ('Read a flow') and then details four distinct views, making it clear what the tool does and how it differs from siblings like list_flows, run_flow, or update_flow. The view-specific details (raw nodes, plain-language summary, execution state, validation problems) strongly differentiate it from other flow-related tools.

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 gives explicit guidance on when to use each view ('Pick the view that answers the question'), including examples like discovering node IDs with 'detail' and checking pre-run problems with 'validation'. It does not explicitly name alternative tools, but the internal view selection provides clear context for choosing this tool's modes, which is slightly less than full 'when vs alternatives' guidance.

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