Skip to main content
Glama

reference_reindex

Rebuilds a model's Visual Studio cross-reference index without compiling, so cross-reference and impact queries return results for existing fields or methods again.

Instructions

Rebuild the Visual Studio cross-reference data for a model (cross-reference-only model build, no compile). Use it when reference_references/reference_impact/reference_graph return nothing for code you know exists, e.g. fields or methods added in an extension model: reindex the model that holds the referencing code, then query again. Needs policies.allowBuilds.

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": {
      "model": "<model>"
    },
    "name": "reference_reindex"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelYesModel whose code should be (re)indexed; its package is derived from the loaded solution.
dryRunNo
timeoutMsNo

Output Schema

NameRequiredDescriptionDefault
okYes
cwdNo
argsNo
kindNo
logsNo
errorNo
indexNo
dryRunNo
signalNo
stderrNo
stdoutNo
targetNo
commandNo
successNo
exitCodeNo
timedOutNo
artifactsNo
cancelledNo
durationMsNo
diagnosticsNo
stderrTruncatedNo
stdoutTruncatedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.16.0

TDQS

A4.3/5.0
Behavior4/5

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

Adds context beyond the annotations: it is a build-class operation ("no compile") and requires policies.allowBuilds, a prerequisite the agent would otherwise not know. It stops short of stating cost/duration or that the existing index is replaced, which matters for an operation whose annotations mark idempotentHint=false.

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?

Three tight sentences ordered as what → when → prerequisite, with zero filler. The colon-chained remediation clause is dense but readable; nothing needs cutting.

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

Completeness4/5

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

For a 3-parameter mutation with an output schema and low schema coverage, the description covers purpose, trigger, and permission prerequisite. The gaps — semantics of dryRun/timeoutMs and expected runtime for a reindex — are minor but real.

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 only 33%: the model parameter is documented, but dryRun and timeoutMs have no descriptions, and the description does not explain them either. What the description does add is choice guidance — reindex the model that holds the referencing code, with the package derived from the loaded solution.

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

Purpose5/5

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

"Rebuild the Visual Studio cross-reference data for a model" gives a specific verb and resource, and the parenthetical "cross-reference-only model build, no compile" disambiguates it from build_model/build_project/build_solution siblings. An agent can tell exactly what this does and what it does not do.

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

Usage Guidelines5/5

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

Explicit trigger condition: use when reference_references/reference_impact/reference_graph return nothing for code you know exists, with a concrete example (fields added in an extension model). It also names which model to reindex (the one holding the referencing code) and the follow-up step (query again).

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