Dice roller, coin flip, random numbers

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

Well beyond the annotations: it discloses the RNG quality (crypto random with rejection sampling, no modulo bias), the seed mechanism that explains reproducible-vs-true-random behavior, and hard limits (100 dice per term, 2–1000 sides, 20 terms, 10,000 numbers). It stops short of stating error behavior for malformed notation or what the seed collision semantics are, so not a 5.

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?

Dense but front-loaded — mode capabilities come first, quality/seed guarantees and limits follow. The trailing web-version URL is arguably filler for an agent choosing a tool, but the rest of the text is high information density with little repetition.

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 10 parameters, no output schema, and three distinct modes, the description covers inputs thoroughly but says nothing about what comes back — totals, individual die faces, dropped dice, streaks, or error payloads for invalid notation. That return-shape gap is the one thing an agent must still guess at.

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 already 100%, so the baseline is 3; the description earns a step up by expanding the `notation` parameter far beyond the schema's single example (d%, dl/kh/kl/dh modifiers) and by restating the numeric-mode constraints on unique/sorted/count. It adds genuine grammar knowledge the schema does not carry.

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 names three specific capabilities (dice rolling, coin flipping, random number generation) and enumerates the exact notation grammar supported (2d6+3, d20, d%, 4d6dl1, 2d20kh1, 5d10dh2). An agent can tell instantly this is a randomness generator rather than a picker, team-splitter, or password tool.

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 context is clear through the mode enumeration and per-mode constraints (dice notation vs. coin counts/streaks vs. numeric ranges with unique/sort). However, it never names an alternative or exclusion — e.g. when to prefer random_pick or random_teams over this tool 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.