Skip to main content
Glama
Sign In

cellmath

by studio.ai.cellmath
OverviewDiscussionsAdmin

sidecar_scan

[PUBLIC WRITE - INGEST PIPELINE STEP 1] Recursively scan a filesystem folder or DB schema to propose new knowledge candidates without modifying source files. WORKFLOW: Step 1: Call sidecar_scan to produce proposed candidates. Step 2: Call sidecar_resolve to accept/reject. Side effects: Creates staging proposals in .braincell/proposed/.

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": {
      "folder": "<folder>"
    },
    "name": "sidecar_scan"
  }
}

Input Schema

NameRequiredDescriptionDefault
folderYesRelative path to scan (e.g. "." or "src").

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / folder / description
      Previous value: -"Relative path to scan."New value: +"Relative path to scan (e.g. \".\" or \"src\")."
  2. Added

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does well: it discloses that source files are unmodified while staging proposals are written to .braincell/proposed/, and the '[PUBLIC WRITE]' tag signals a mutating, externally visible operation. It stops short of stating idempotency (does re-running duplicate proposals?), recursion scope (symlinks, ignored paths), or permission requirements — gaps that matter for a recursive write-triggering scan.

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?

Front-loaded with the access tag, then purpose, then numbered workflow, then side effects — a sensible information hierarchy with little waste. The bracketed tag and the 'INGEST PIPELINE STEP 1' framing are dense but each carries routing value.

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 one-parameter tool with no annotations and no output schema, the description covers purpose, sequencing, and side effects, which is most of what an agent needs to invoke it safely. It leaves the return shape of 'proposed candidates' and failure modes unstated, but the pipeline handoff to sidecar_resolve partially compensates.

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% and the single 'folder' parameter is already documented with path examples, so the schema does the heavy lifting. The description adds that a DB schema (not just a filesystem path) may be targeted, which is genuine extra meaning, but it slightly conflicts with the schema's 'Relative path to scan' wording and never clarifies how a schema identifier is expressed.

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?

The description names a specific verb and resource ('Recursively scan a filesystem folder or DB schema') and states the output ('propose new knowledge candidates'), plus an explicit non-goal ('without modifying source files'). It also distinguishes itself from its pipeline partner sidecar_resolve by labeling itself STEP 1, so an agent can separate the two without inspecting either schema.

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?

The WORKFLOW block gives explicit when-to-use instructions (call this first to produce candidates) and names the alternative/next step (sidecar_resolve to accept/reject). This is a full routing instruction rather than an implied context.

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

All cellmath toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources