mdan_state_update

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

With no annotations, the description carries the behavioral disclosure burden. It discloses the write nature and the side-effect that completed artifacts are registered in the context graph. However, it does not explain state transitions, whether 'start' resets existing progress, or whether 'complete' validates artifacts.

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 a single compact sentence that front-loads the core purpose and then enumerates the lifecycle actions. Every element earns its place, with no filler or repetition.

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 six-parameter state-update tool with no output schema and no annotations, the description covers the main invocation semantics and the notable graph side-effect. Minor gaps remain, such as allowed action ordering and return behavior, but the core usage is sufficiently 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?

Schema coverage is 67%, so the description must add some meaning beyond schema descriptions. It usefully explains the action enum values and the role of artifacts at completion, but it adds little for step, summary, stepFile, or workflow beyond what the schema already states.

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 identifies the tool as recording workflow progress, with distinct lifecycle actions ('start', 'step', 'complete') and a mention of artifact registration. It does not explicitly contrast with siblings like mdan_run_workflow, so differentiation is implied rather than stated.

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 gives explicit trigger conditions for each action: start/resume a workflow, step when moving to a step, complete with produced artifacts. It lacks explicit exclusions or named alternatives, but the action-specific usage context is clear enough for selection.

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