bisect_bad

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

No annotations are provided, so the description carries full burden. It discloses key behaviors: marking as BAD, narrowing bisection, enabling next subset, and reporting culprit. However, it lacks explicit mention of required prior state (e.g., bisection must be started) or possible errors, which are important for a mutation tool.

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 three sentences with clear structure: purpose, effect, resolution. Every sentence contributes value with no redundancy or clutter.

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 zero parameters and no output schema, the description covers the essential purpose and progression. It could be improved by mentioning prerequisites (e.g., 'must have started bisection') or error conditions, but overall it is sufficiently complete for a simple tool within a bisection workflow.

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?

The tool has zero parameters, and the description adds no param info beyond the empty schema. This is appropriate and complete for a parameterless tool.

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 action ('mark as BAD'), the resource ('currently enabled set of custom nodes'), and the effect (narrows bisection, enables next subset, reports culprit). It distinguishes from siblings like bisect_good and bisect_start by specifying the 'BAD' marking and resolution behavior.

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 implies when to use (after finding the problem present with the set) and describes the progression (narrows, enables next, resolves). It does not explicitly contrast with alternatives like bisect_good or mention prerequisites like bisect_start, but the context of bisection makes usage clear.

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