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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does this exceptionally well: it explains the algorithm for each operation (e.g., 'unbiased integers via rejection sampling', 'Fisher-Yates', 'chi-squared conformance proof'), specifies constraints (count limits, encoding options), and notes that the top-level seed makes draws reproducible. This goes far beyond a generic 'generates random data' and gives the agent a precise model of behavior.

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?

The description is compact yet comprehensive, using a clear list format that front-loads the core purpose ('Direct randomness') and then details each operation. Each line is purposeful, with no fluff or repetition. The structure makes it easy for an agent to scan and identify the relevant operation quickly.

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 tool with six distinct operations, nested params, and no output schema, the description covers all essential aspects: operation selection, parameter requirements, constraints, and even output semantics (e.g., shuffle's permutation meaning). It also mentions reproducibility via seed. Nothing critical is missing for an agent to call this tool correctly.

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?

The input schema only defines operation, params, and seed with generic descriptions. The description adds rich semantics for every operation's parameters, such as 'bytes -- raw CSPRNG bytes. params: {count<=4096, encoding: hex|base64}' and 'int -- unbiased integers in [min,max] via rejection sampling. params: {min, max, count<=10000}'. This fully compensates for the 67% schema coverage and provides meaning far beyond the 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 opens with 'Direct randomness' and then enumerates six specific operations (bytes, int, shuffle, choose, sample, constrained) with one-line explanations. This clearly states the tool's purpose and distinguishes it from the sibling tools (commitment, explore, test), which are unrelated to randomness. The verb 'selects' and the resource 'primitive' make the function explicit.

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 description provides clear context: this tool is for generating random values via various primitives. It doesn't explicitly mention when not to use it or name alternatives, but since the sibling tools are unrelated, the usage context is unambiguous. The lack of explicit exclusions is acceptable given the tool's self-contained nature.

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