session.resume

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

The annotations (destructiveHint=true, readOnlyHint=false, idempotentHint=false) are supplemented with rich behavioral context: the command is gated and requires local user approval, a client cannot approve its own request, it retries the same request id after approval, and per-request checks/policy still apply. This is exactly the operational nuance an agent needs before invoking a destructive, externally-gated command.

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?

Three tight sentences: identity/risk, the approval flow with retry semantics, and residual requirements. The critical user-approval constraint is front-loaded, and every sentence carries unique information with no filler. The telegraphic 'Risk: gated; maturity: L3' is the only slight blemish.

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?

The hardest aspect of this tool — the approval/retry flow — is covered thoroughly, and the output schema handles return values. However, the description never states what resuming does to session state or what happens when no approval is pending, and _expectedSceneRevision's role is left entirely to the schema. An agent can execute the flow but may not fully grasp the operation's effect.

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 75% — _requestId, _authorization, and _transactionId are already documented in the schema, leaving only _expectedSceneRevision bare. The description adds no parameter-level details, though 'retries the same request id after the user approves it' does reinforce the _requestId replay-safety semantics. With high schema coverage, the baseline of 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 identifies the tool as "PartMe Blender Harness command `session.resume`" but never states what resuming a session actually does — no verb+resource explanation such as 'resumes a paused or gated session' or description of the resulting state change. The text restates the title and immediately shifts to approval gating and retry behavior, so the core purpose is left to inference from the command name.

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?

No when-to-use guidance or alternatives are provided. The approval requirement and 'risk: gated' imply invocation in a user-approval flow, but the description never says when to call this tool versus siblings like blender_job_resume, blender_session_pause, or the transaction tools. 'Per-request argument checks and session policy still apply' is a constraint, not usage guidance.

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