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

Annotations already declare read-only, idempotent, non-destructive behavior, but the description adds valuable details beyond them: deterministic hashing with caching, metering on the run rather than the bars, per-market default windows, and a 6,000-bar cap. It does not contradict annotations and adds meaningful operational context.

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 dense but front-loads the core operation and avoids filler. It is a single long paragraph rather than structured sections, but every sentence carries operational information relevant to invoking the tool.

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 9-parameter rehearsal tool with no output schema, the description explains the returned frames and summary in enough detail, along with determinism and default windows. It does not cover error behavior or validation failure modes, but it is otherwise complete enough for correct invocation.

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 baseline is 3, but the description adds cross-parameter meaning: window defaults differ for NQ/ES vs crypto, `hours` is crypto-only, `frames` returns from the end with a max of 600, `params` replaces defaults within min..max and changes the hash, and `script` vs `example` are mutually alternative inputs.

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: 'Step a cubicle.script v1 over the deck's own bars with the deterministic reference runner.' It is clearly a rehearsal/backtest operation, but it does not explicitly contrast itself with siblings like script_validate or replay_open, so sibling differentiation is only implicit.

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 operational context such as passing a script or a bundled example and the default windows per market, but it never states when to use this tool versus alternatives. Usage is implied by the 'rehearse' framing rather than explicitly guided.

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