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

With no annotations, the description carries the full load and does so well: it discloses the CSPRNG plus rejection sampling, explains why that matters for fairness versus a plain modulo, and states the cost model ($0.005 per call, paid over x402 in USDC) — an unusual and important operational constraint. It stops short of stating latency, limits on simultaneous calls, or failure behavior when payment is missing.

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?

Front-loaded with the when-to-use clause, then fairness rationale, then exclusions, then pricing — a logical order with no filler. The first sentence is dense and run-on, packing trigger, output shape, and examples into one breath, which slightly hurts scanability.

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?

A two-optional-parameter tool with no output schema and no annotations is fully covered: the description explains the return payload (per-die rolls, total, notation), the randomness guarantee, and the payment requirement. An agent has everything needed to invoke it and interpret results.

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% and both parameters are documented with ranges and defaults in the schema itself, so the description only adds the framing 'any number of faces'. Baseline 3 applies, with modest extra credit because the notation output (3d6) implicitly links count and faces to the result format.

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 (roll dice with any number of faces) and immediately differentiates from siblings by naming /v1/random/pick and /v1/random/password as the wrong tools. The returned artifacts (individual rolls, total, standard notation like 3d6) further pin down what the tool produces.

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?

Explicit trigger is given ('when an agent has to produce a roll a player or an audit will check'), and two explicit exclusions route the agent to random_pick for choosing from a list and random_password for secrets. Nothing is left to inference about when this tool is the right choice.

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