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

Annotations only say readOnlyHint=false and idempotentHint=false; the description explains the surprising reason ('not marked read-only because each call is charged') and adds pricing, a free-tier quota, and a 'failed calls free' billing rule. It also discloses the return content ('each result and the totals') absent an output schema. This is exactly the context annotations cannot carry.

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?

Six short, front-loaded sentences covering purpose, return, usage, example, billing, and read-only rationale; nothing is redundant. The billing sentence is the only one that could be trimmed for a pure-selection decision, but it earns its place by explaining the annotation.

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 single-optional-parameter tool with no output schema, the description covers purpose, return values, pricing, and the read-only rationale, leaving little for an agent to guess. Only the exact return shape (e.g., per-coin array vs. summary counts) is left slightly loose.

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 description coverage is 100% and the count parameter already documents the 1-100 range and default, so the schema does the heavy lifting. The description only restates this with 'Example: count=1' and adds no new semantics such as behavior for count>1 beyond the totals mention.

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 concrete verb and resource ('Flip one or more fair coins') plus the implementation detail of a cryptographic random source, which separates it from a naive random number generator. It does not explicitly name siblings like dice, random_number, or magic_8_ball, so the agent must infer the boundary from 'fair decisions and games'.

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 fair decisions and games' implies a domain but gives no when-not guidance or named alternative (e.g., dice for non-binary outcomes, random_number for ranges). The 'Example: count=1' is an invocation hint rather than routing guidance.

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