utilpeek: cryptographically strong random numbers, bytes, UUIDs, dice rolls, picks and shuffles

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered; the description goes well beyond that by disclosing that validation errors return 422 before any payment (not charged), that nothing is stored or logged, expected latency (<0.1 s), the price (USD 0.001) and a free tier (10 calls/IP/UTC day). These are exactly the kind of non-indexed operational traits an agent needs.

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?

Purpose is front-loaded, followed by the sibling redirect, then mechanics, then constraints/pricing. Every sentence carries information (source, defaults, limits, 422 semantics, no-logging, price). It is dense rather than padded, though it packs a lot into a single flowing block and could be marginally tightened.

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 an output schema present, return-value explanation is unnecessary, and the description still covers the essential caller questions: what defaults apply, how errors surface (422, uncharged), durability (nothing stored/logged), latency and cost. For a 9-parameter tool with zero required params, it leaves nothing material for the agent to guess.

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 schema already documents each parameter and a baseline of 3 applies. The description nonetheless adds meaning beyond it: integer ranges are inclusive vs. floats being [min, max), the dice expression grammar (3d6 / 2d10+3 returning the total), the 1-1,024 byte bounds and the behavior of an empty body (one integer 0-100). This is real added value on top of an already-complete 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?

The description states a specific verb and resource (generate cryptographically strong random numbers, bytes, UUIDs, dice, picks, shuffles) and immediately names the sibling it does NOT cover (generate_ids for UUIDs/ULIDs in the sense of id generation). The CSPRNG source (OS CSPRNG via Python `secrets`) is explicit, so the agent knows this is a security-grade random tool, not a pseudo-random one.

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?

It routes clearly to a sibling: 'For UUIDs and ULIDs use generate_ids' — a concrete when-to-use-another-tool rule. It also documents the default empty-body behavior (one integer 0-100) and advises 'Generate secret keys locally', which is actionable guidance. It lacks explicit when-not conditions beyond the id-generation redirect, but the context is clear.

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