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

Annotations only say readOnlyHint/openWorldHint; the description adds far more: nothing is persisted, success yields a token that expires in 10 minutes and is byte-bound, and failures return per-error workarounds. That is exactly the side-effect and lifecycle detail an agent needs and cannot get from the annotations.

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 paragraphs, front-loaded with the action and the no-persistence caveat, then the success/failure contract. No filler sentences.

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 single-param, nested-object tool with an output schema and readOnly annotations, the description covers the remaining unknowns: what it does and doesn't persist, what success returns, the token's lifetime and binding, and the failure error shape.

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 adds real semantics: the definition passed must be the exact bytes you intend to create, since the token is bound to them. It also names get_node_info indirectly via the schema for building the graph.

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+resource ('check a workflow definition') and immediately scopes it: it applies the same gates a run start applies and 'Saves nothing'. This cleanly separates it from create_workflow and run_workflow, which do persist or execute.

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?

Explicitly ties the tool to its successor: the success token is what 'create_workflow requires', and 'validate what you will create' tells the agent to run this before creating. It stops short of an explicit when-not-to-use statement (e.g., that it is unnecessary for an already-validated or fetched definition), so it's clear context but not full routing.

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