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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description reinforces this with the note that repeated calls are safe until done=true, i.e. idempotent polling. It also discloses the default/max timeout and the rationale (fitting hosts with a 60 s tool timeout), real behavioral context beyond the annotations. It does not mention the private-key authorization requirements the schema hints at.

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?

Three tight sentences: behavior and timeout budget first, then the return shape, then the polling-safety note. No filler and nothing buried.

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 correctly carries the return contract (payment confirmations, spec acceptance, running instances with URLs) and the timeout semantics. The remaining gap is authorization context for the private-key parameters, though the schema provides per-parameter guidance.

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 67%, so the schema already documents txid, previousHash, and the private keys. The description adds genuine meaning only for timeoutSeconds (default 45, max 600, chosen to fit host timeouts) and implies what txid is for by describing the returned payment confirmations. Baseline 3 for a partially documented 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 (polls the network for a deployment to be accepted and its instances to run) plus the scope of polling via timeoutSeconds. The wait/poll framing separates it cleanly from sibling reads like flux_get_app and writes like flux_deploy_app.

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?

"Safe to call repeatedly until done=true" gives a clear polling-loop usage pattern, which is the key operational guidance. However, it never names an alternative (e.g. flux_get_app for a single check) or states when not to use this tool, so routing against siblings is left to inference.

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