Start Pipeline Session

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

The description goes far beyond the annotations (which are all false) by disclosing the critical limitation that the returned pipeline_id is not linked to later evaluate_* calls and that there is no server-side session state. It also adds the cost ($0.05) and clarifies it is an identifier/timestamp issuer, not an active tracking session. This is exceptional behavioral transparency.

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 well-structured: the cost and core purpose are front-loaded, followed by the critical limitation and usage guidance. Every sentence adds value, and the length is appropriate given the need to correct a likely misconception about session linkage.

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?

Given the tool's low complexity (simple ID generator) and the presence of an output schema, the description fully covers what the tool does, its limitations, and the intended usage. It is complete enough for an agent to decide when and how to use it without additional information.

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%, so the parameters are already fully documented. The description adds no param-specific details beyond what the schema provides, such as how to use scope or ttl_seconds. It does mention 'scope, expiry, initial drift_mode' as part of the returned metadata, but this is output context, not parameter semantics. Baseline 3 is appropriate.

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 generates a new pipeline_id and returns session metadata for grouping related checks. It explicitly distinguishes itself from the sibling evaluate_* tools by framing this as a session/pipeline starter, not an evaluation tool. The verb 'generates' and the resource 'pipeline_id' are specific and unambiguous.

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 when-to-use guidance: 'Use this to obtain a shared reference ID for your own client-side grouping of a multi-step audit sequence.' It also provides a clear when-not: 'do not rely on it to automatically aggregate drift across calls.' It does not name alternative tools, but the context makes the appropriate use clear.

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