run_repository_pipeline

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

Annotations only include false hints for readOnly, openWorld, idempotent, and destructive, which are not very informative. The description adds significant behavioral context: it details the chain of stages, the return envelope contents (response, timings, ids), how stop_after halts early (with specific side effects like skipping the planner or simulate), and the ability to reuse snapshots. This goes beyond the annotations and provides insight into the tool's side effects and data flow.

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 relatively long but each sentence introduces a distinct concept: the chain and return envelope, snapshot handling, stop_after behavior, parameter mirroring, and the guidance to use single-stage tools. The most critical information (purpose, snapshot id, stop_after) is front-loaded, and the final guidance sentence is a useful addition without unnecessary fluff.

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 complexity of an 11-parameter orchestration tool with nested objects and no output schema, the description covers the essential aspects: what the tool does, how to control the chain, how to handle snapshots, and when to use alternatives. It doesn't detail the exact format of the envelope or how errors propagate, but with no output schema, that might be a minor gap. It provides enough for an agent to call correctly in most cases.

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 100% with rich descriptions for each parameter, so the baseline is 3. The description adds value by explaining how parameters interact: e.g., passing snapshot_id vs snapshot, stop_after values and their effect on subsequent stages, and that 'runs' and 'seed' mirror standalone tools. This clarifies the orchestration semantics beyond the raw schema.

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 function: runs the entire repository-intelligence chain (snapshot, triage, plan, simulate) in one call, returning a canonical envelope with stage responses, timings, and ids. It mentions specific stage names and the resources involved, making it easy to distinguish from the single-stage tools like triage_repository and simulate_repository.

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 explicitly states when to use this tool versus alternatives: 'Use the single-stage tools when you need to inspect or adjust between stages.' It also explains the key parameters (snapshot_id vs snapshot, stop_after) and how they affect the chain. This provides clear guidance on when to choose this orchestration tool over its components.

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