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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. On top of that the description discloses that it returns 'the blocking errors' with each error naming the node and the port, and that nothing is executed — useful behavioral context beyond the annotations. It stops short of saying whether non-blocking warnings are reported or how the result is shaped.

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 sentence, front-loaded with the question the tool answers, followed by a compact em-dash list of error types. Every clause earns its place and nothing is padded.

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 output schema, the description carries the burden of explaining the return: it states the tool returns blocking errors, each naming node and port. The very rich graph schema documents the input fully. The only gap is that the full shape of the response (beyond error naming) and treatment of warnings is left unspecified.

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% and the graph/_files/_subject objects are exhaustively documented in the schema itself. The description adds no parameter-level detail (no mention of graph structure, _files, or _subject), 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 (validate a workflow graph) and frames the question the tool answers: 'Would this workflow graph run?' It also enumerates the exact failure classes it reports (unknown tool, wire into a nonexistent port, cycle), which cleanly separates it from run_workflow by the closing phrase 'without running anything.'

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 phrase 'without running anything' establishes the context — this is the pre-flight, non-executing check — which implies its relationship to run_workflow. However, it never names run_workflow as the alternative or states explicitly when a validation pass should precede execution, so the selection guidance is implied rather than spelled out.

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