workflow.start

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

No annotations exist, so the description must carry the full transparency burden. It discloses that 'existing state is protected unless replace=true', and mentions 'first-use setup plus deterministic routing are enforced' – useful behavioral hints. But it does not explain the concrete side effects (e.g., whether it writes to the repo, needs auth, or returns a workflow ID), leaving gaps an agent would need to call it safely.

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 compact – three sentences that cover purpose, usage, parameter hints, and key behavior in a front-loaded way. There is no fluff or tautology. Slight denseness in the third sentence keeps it from a 5, but it is well structured.

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 tool with 6 parameters, no annotations, and no output schema, the description gives a reasonable overview but not enough for complete autonomous invocation. It clarifies when to use it and some behavior, but terms like 'first-use setup' and 'deterministic routing' are left undefined, and there's no guidance on expected return values or failure modes.

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 0%, so the description must compensate. It adds meaning for session_span and route_clarity by instructing the agent to classify them from the conversation/repository, and for replace by explaining it overrides protected state. However, it gives no added meaning for goal, repo_path, or decisions_settled beyond what their names and types imply, so compensation is partial.

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 and resource: 'Start durable guided-development state for a new software goal.' It also provides the trigger condition ('when the user wants development guidance or does not know the next step'), which clearly separates it from siblings like process.start or task.create. The word 'durable' and the focus on 'development guidance' make the tool's role distinct, even without naming alternatives directly.

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 usage context: 'Use this when the user wants development guidance or does not know the next step.' This tells the agent when to invoke the tool. However, it does not name alternative tools or exclusion conditions (e.g., when to use workflow.update or workflow.guide instead), so it lacks the when-not guidance needed for a 5.

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