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

With readOnlyHint=true and openWorldHint=false already declared, the description still earns credit for two non-obvious facts: nothing is spent and no work is executed, and the check itself is billed per call via x402 when payments are enabled. What is missing is any hint at the response shape (allow/deny, which term failed, the estimated price), which matters because there is no output schema.

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 compact sentences: a framing question, the operational answer, and the payment caveat. Front-loaded and every clause carries information — no restatement of the title or filler.

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 five-parameter, read-only dry run with no output schema, the definition covers purpose, cost, and side-effect profile adequately. The notable remaining gap is that an agent cannot tell what it will receive back or how a denial is reported, which is exactly the information a dry-run tool exists to deliver.

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 80% and the schema already documents policy options, backend 'auto' vs id, problem, and the qm_... mandate id. The description adds only indirect meaning — that policy/backend drive which backend the router picks and that shots feed the price estimate — rather than clarifying any single parameter. Baseline 3 is appropriate.

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 pairs a specific verb phrase ('estimates the price and checks it against every term') with the object (the mandate) and explicitly frames the operation as a dry run that spends nothing. This distinguishes it cleanly from quantum_run_hardware, quantum_optimize and quantum_mandate_status without opening any schema.

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?

Usage is well signalled: this is the pre-flight gate for a paid run, and the reader is pointed to quantum_pricing for payment details. It stops short of naming the state-management siblings (quantum_mandate_status / quantum_mandate_request) or saying what to do when the check fails, so the when-not path is left implicit.

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