reelier_replay

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

No annotations provided, so description carries full burden. It thoroughly explains Level 0 replay, zero LLM calls, reproduction of tool calls only, read-only default, and handling of idempotent-write steps. It also discloses that it never fabricates a pass and reports drift reasons.

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 generally concise and front-loaded with the main action. It uses multiple sentences but avoids excessive verbosity. Could be slightly tighter, but still efficient.

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?

No output schema, but description clearly states what the return value includes: per-step outcomes, timing, totals, and failure reasons. It covers key aspects like templating, read-only safety, and idempotent-write handling. Minor omission of error scenarios.

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 schema descriptions exist for all parameters. The description adds context for vars (templating), allowWrites (read-only default), and wrap (MCP server connections), but these are already clear from schema. Baseline 3 is appropriate.

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 clearly states the tool runs a skill file at Level 0 deterministic replay, returning the run record. It specifies the verb 'run' and resource 'skill file'. It distinguishes from siblings by noting it does not schedule itself and is read-only by default, but does not explicitly compare to reelier_scan or reelier_push.

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?

Provides guidance on when to use: for deterministic replay with zero LLM calls, and mentions pairing with cron/CI for recurring runs. It explains how to pass templated vars and the read-only nature with allowWrites option. However, does not explicitly differentiate from sibling tools.

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