resume_session

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

No annotations are provided, so the description carries the full burden. It discloses key behaviors: re-runs the pipeline from start_stage, writes a new revision while leaving prior revisions untouched, spends 'real LLM budget' and 'takes minutes.' It also details the return values, offering significant transparency beyond a minimal description.

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 front-loaded with a purpose sentence and then uses a concise Args block for parameters. While a little longer than strictly necessary, each sentence provides actionable information and there is no fluff.

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 description covers prerequisites (checkpoints on disk), cost/time tradeoffs, alternative tools, parameter semantics, and return values. Given the tool's moderate complexity and the absence of annotations/output schema detail, the description is thoroughly complete.

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?

The schema provides no descriptions (0% coverage), but the tool description documents every parameter in the Args section: scene_hash is sourced from list_sessions or generate_scene, start_stage lists valid stage values, and stop_stage explains optionality and default behavior ('omit to run to the end'). This fully compensates for the schema gap.

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 opens with a specific verb-resource pair: 'Resume an existing generation session from a stage checkpoint.' It clearly states the tool's primary function and distinguishes it from the sibling generate_scene by noting it is 'Cheaper than generate_scene when only later stages need to change.'

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?

It explicitly states when to prefer this tool over generate_scene, saying it is cheaper when only later stages need to change. It also indicates that it uses checkpoints already on disk, and mentions that scene_hash comes from list_sessions or generate_scene, providing clear usage context and alternatives.

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