Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

bisect_start

Start a bisect session to find where a design, preset, or feature broke by comparing a known good version with a bad descendant and checking candidate versions.

Instructions

Start a new bisect session — find where something broke.

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": {
      "artifact_type": "<artifact_type>",
      "artifact_id": "<artifact_id>",
      "good_version_id": "<good_version_id>",
      "bad_version_id": "<bad_version_id>"
    },
    "name": "bisect_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
operatorNoWho is running the bisect, kept on the session. Optional: omitted, none is recorded.
artifact_idYesThe id of the design, preset or feature whose versions are searched.
target_checkNoThe name of a spec check to follow, as it appears in the design's checks (designs only; refused for a preset or feature). Omitted, the session waits for a verdict on each candidate.
artifact_typeYesWhich version graph to search: ``design``, ``preset`` or ``feature``; any other word is refused.
bad_version_idYesA version known to be bad; it must descend from ``good_version_id``.
good_version_idYesA version known to be good: the older end of the range.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv1.5.1
    • addedInput schema / properties / artifact_id / description
      Added value: +"The id of the design, preset or feature whose versions are searched."
    • addedInput schema / properties / artifact_type / description
      Added value: +"Which version graph to search: ``design``, ``preset`` or ``feature``; any other word is refused."
    • addedInput schema / properties / bad_version_id / description
      Added value: +"A version known to be bad; it must descend from ``good_version_id``."
    • addedInput schema / properties / good_version_id / description
      Added value: +"A version known to be good: the older end of the range."
    • addedInput schema / properties / operator / description
      Added value: +"Who is running the bisect, kept on the session. Optional: omitted, none is recorded."
    • addedInput schema / properties / target_check / description
      Added value: +"The name of a spec check to follow, as it appears in the design's checks (designs only; refused for a preset or feature).  Omitted, the session waits for a verdict on each candidate."
  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 declare readOnly=false, destructive=false and openWorld=false, so the safety profile is already covered; the description usefully adds the Kiln Pro entitlement requirement. It does not disclose that a persistent session is created and stored (with an operator field retained), nor how target_check changes candidate evaluation, which the schema alludes to but the description never surfaces.

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 lines, verb-led and front-loaded, with the entitlement note placed after the core purpose. Nothing is wasted, though the brevity borders on under-specification for a session-creating tool.

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?

With 6 parameters, 4 required, no output schema, and a session lifecycle that other tools depend on, the description should say what starting a session produces and that bisect_good/bisect_bad/bisect_end follow. The schema covers the inputs well, but the workflow context an agent needs to use this correctly is absent.

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 description coverage is 100%, including the descent constraint on bad_version_id, allowed artifact_type values, and target_check being designs-only. The description adds no parameter meaning beyond that, so the baseline of 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 states a concrete verb and resource — "Start a new bisect session" — plus the intent ("find where something broke"), which distinguishes it from bisect_good, bisect_bad, bisect_skip and bisect_end that operate on an existing session. It stops short of naming those siblings or explaining how the session lifecycle continues.

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?

"Needs Kiln Pro" is a real prerequisite gate that saves a failed call, but there is no explicit when-to-use guidance versus the other bisect_* tools, nor a statement of what must come next (marking good/bad versions). The agent must infer the workflow from sibling names.

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