start_run

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

Without annotations, the description carries the burden. It discloses clearing previous events, returning a run_id, and automatic logging of subsequent calls. This is good, but could mention idempotency or re-calling behavior.

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 concise with five sentences, each serving a purpose: stating purpose, usage timing, side effects, and context. No wasted words, front-loaded with essential information.

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?

With an output schema (not shown) and one parameter, the description covers initialization behavior and logging side effects. It lacks details on parameter semantics and whether this step must be followed by finalize_run, but the sibling list provides context.

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 add meaning to the single 'query' parameter. The description mentions 'for a user query' but does not specify what the query string should contain (e.g., raw user question, formatted query). This leaves ambiguity.

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 states the tool's purpose: 'Begin a new audit run for a user query.' It further specifies to call at the start of each user question, distinguishing it from siblings like finalize_run and get_audit_trail.

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 provides explicit usage guidance: 'Call once at the start of each user question.' It implies this is a setup step, but does not explicitly exclude other uses or mention alternatives, though context suffices.

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