start_workflow

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Intelligent role-based guidance' hints at behavior but is vague—does it auto-assign roles? Does it fail without a role defined? What side effects occur (state changes, task triggers, notifications)? No behavioral detail about execution lifecycle, idempotency, or whether starting an already-running workflow is an error is disclosed.

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?

Single sentence, front-loaded with the primary action, zero wasted words. It's concise and efficient, though the 'intelligent role-based guidance' phrase adds marketing tone without concrete technical value.

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 workflow-starting tool with moderate complexity (3 params, nested context object), the minimal description is somewhat adequate given strong schema coverage, but it lacks important context: the relationship to role guidance (what roles are involved), failure modes, and relationship to sibling workflow tools like auto_detect_workflow and transition_role_workflow. With no output schema and no annotations, more behavioral context is warranted.

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 100% and includes decent per-parameter descriptions (workflowId, agentType with enum and default, context with additionalProperties). The description adds 'role-based guidance' context that relates to role semantics but doesn't explain how context or agentType affect execution beyond their schema descriptions. Baseline 3 is appropriate given the strong schema coverage.

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 states a specific verb+resource ('Start a new Anubis workflow execution') with a distinctive qualifier ('intelligent role-based guidance'), which distinguishes it from siblings like manage_execution and pause_execution. It's clear but doesn't fully differentiate from auto_detect_workflow or get_guidance, which could overlap in intent.

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 explicit guidance on when to use this tool vs alternatives. The description mentions 'intelligent role-based guidance' which implies this tool provides role-aware execution, but it doesn't explicitly name alternatives or exclude situations (e.g., when to use auto_detect_workflow instead, or whether this replaces pause/resume workflows). Siblings like start workflow vs manage_execution create ambiguity unresolved by the description.

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