Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

bisect_bad

Mark the current or specified version as known-bad in a Kiln bisect session to narrow down the first faulty revision (requires Kiln Pro).

Instructions

Mark the current (or explicit) candidate as known-bad.

Needs Kiln Pro.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "session_id": "<session_id>"
    },
    "name": "bisect_bad"
  }
}

Input Schema

NameRequiredDescriptionDefault
session_idYesThe bisect session's id, as ``bisect_start`` or ``list_bisect_sessions`` returned it.
version_idNoThe version to mark bad. Omitted, the session's current candidate; a version already marked the opposite way is refused.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.5.1
    • addedInput schema / properties / session_id / description
      Added value: +"The bisect session's id, as ``bisect_start`` or ``list_bisect_sessions`` returned it."
    • addedInput schema / properties / version_id / description
      Added value: +"The version to mark bad.  Omitted, the session's current candidate; a version already marked the opposite way is refused."
  2. Addedv1.5.0

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already establish that this is a non-read-only, non-destructive, closed-world mutation, so the safety profile is largely covered. The description adds the useful 'Needs Kiln Pro' entitlement gate, but it does not say whether bad marks can be revised, whether the call advances the session, or what happens when every candidate is exhausted.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with the action front-loaded and the entitlement constraint trailing as a cheap caveat. Nothing is padded, though the second sentence could have been spent on behavior rather than a bare gate notice.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-parameter state-mutation tool with full schema coverage and annotations, the definition is callable as written. It still leaves the post-call picture unclear: whether a next candidate is auto-selected or whether bisect_current must be called, which matters for correct sequencing in the bisect workflow.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so both parameters are already documented, including the session_id source and the version_id default. The description's 'current (or explicit) candidate' phrasing reinforces the default behavior but adds no syntax or semantics beyond the schema. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and object: mark the current or explicitly named bisect candidate as known-bad. That is clearly distinct from siblings like bisect_good and bisect_skip without needing to name them. It does not explicitly reference the sibling tools, but the polarity is unambiguous from the wording.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than stated: the agent must infer this is called mid-session, after bisect_start and before bisect_end. The 'Needs Kiln Pro' line is a genuine prerequisite worth having, but there is no explicit when-not or pointer to bisect_good/bisect_skip as alternatives.

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

Deploy Server

Other Tools