bicameral_begin

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

With no annotations provided, the description carries the full burden. It discloses that the tool routes each step to the user or editor model, runs baseline verification, and returns routing. It also explains the pin=true behavior and the editor_model='self' option. It doesn't mention side effects like whether a run is persisted or whether it modifies state, but it covers the key behavioral traits.

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 two sentences and front-loads the core purpose. It packs useful routing and pin behavior into a compact form. It could be slightly more structured, but it earns its place without redundancy.

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?

The tool has 10 parameters, no annotations, and an output schema. The description explains the high-level flow but leaves many parameters unexplained (task_kind, gates, commit, learning, verify_command, summary). An agent would need to infer their meaning from names alone. The output schema exists, so return values are covered, but the parameter semantics gap makes this incomplete for a complex tool.

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 explains editor_model and pin semantics, but the other 8 parameters (task, workspace, task_kind, summary, steps, gates, commit, learning, verify_command) are not described in the tool description. The schema itself has descriptions for nested StepInput properties, but top-level parameters lack descriptions. The description adds some meaning but doesn't fully compensate for the 0% 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 ('Register your plan and start a run') and resource, and clearly distinguishes this tool from siblings by explaining it is the entry point that routes steps and runs baseline verification. It also names the editor_model='self' option, which differentiates it from other bicameral tools.

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 explains when to use this tool: to register a plan and start a run, and it gives a clear alternative behavior (editor_model='self' to do every step yourself). It doesn't explicitly name sibling tools as alternatives or state when not to use it, but the context is clear enough for an agent to select it as the initial run tool.

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