Plan or Replay a Recorded Session's Tool Calls

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

Annotations declare destructive=true / readOnly=false, and the description richly extends this: mutating tools are flagged blockedByDefault and skipped, failed steps are never replayed, replayed steps are recorded into the CURRENT session, and explicit-mutation-approval is required. This is real behavioral context beyond the annotation flags, with no contradiction.

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?

Core semantics are front-loaded and tight. However, the appended metadata block (Phase/cost/idempotency/Produces/Verify/On-failure) and the signature line that restates the schema params are templated padding that dilutes an otherwise crisp description.

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 complex, state-changing tool with no output schema, it covers safety, approval requirements, and chain-to-playbook flow well. It does not describe the shape of the returned 'structured plan', which is the main piece an agent might still need.

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 both `dryRun` and `includeMutating` defaults are already documented in the schema. The description adds a useful signature recap and reinforces the defaults, but adds no syntax or format detail beyond what the schema provides — baseline 3.

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 pair (read/plan vs re-issue) on a specific resource (a recorded session's tool-call trace), and makes the default behavior explicit. It is clearly distinguishable from siblings like playbook-run or execute, since it operates on an existing session trace.

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?

Gives explicit when/when-not: default is planning, `dryRun: false` to actually replay, `includeMutating: true` needed for side-effecting steps, and failed steps are never replayed. It names `playbook-save` as the chaining alternative and states session-replay refuses to call itself.

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