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

Annotations cover safety and idempotency, but the description adds real behavioral context: cryptographic random source, per-roll return shape (every roll, the modifier, the total), and the charging model including that repeats are not free — which meaningfully explains why idempotentHint=false matters. It also states failed calls are free, which matters for retry 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?

Front-loaded with the capability, format, and limits, then usage, then pricing. Every sentence carries information, though 'Reads or computes only and changes nothing' overlaps with readOnlyHint=true and the pricing sentence is dense relative to the core purpose.

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 one-parameter tool with no output schema, the description covers input format, bounds, what is returned, safety profile, and cost — everything needed to call it correctly and predict the response.

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% with a single documented parameter, so the baseline is 3, and the description adds bounds not present in the schema (up to 100 dice of up to 1000 sides) plus a second notation example. It doesn't restate the default (1d6), which is already in 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?

States a specific verb and resource ('Roll dice') plus the exact input format ('standard notation such as 2d6+3 or 1d20') and hard limits (100 dice, 1000 sides). This clearly separates it from siblings like random_number, random_pick, or coin, which don't take dice notation.

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?

'Use for tabletop games and simulations' plus a concrete example ('roll=2d6+3') gives an agent a clear context for selecting it. It stops short of explicit exclusions or naming an alternative (e.g., 'for a single uniform integer use random_number'), so it isn't a full when/when-not statement.

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