Skip to main content
Glama

Code that matters most to the files you are changing

graph_relevant
Read-only

Find the functions and classes most relevant to files you plan to change, ranked by importance with signatures, locations, and call relationships, so you know what else to read before editing.

Instructions

The functions and classes elsewhere in the repository that matter most to the given files, most important first, cut to a token budget: each with its signature, file and line, plain-English summary, how it relates to the files (calls them, called by them) and its area. Use it before editing to know what else to read. Returns JSON. Read-only and local.

Works without SKYLOS_API_KEY and has no daily limit: it reads the repository on this machine and sends nothing to Skylos Cloud.

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": {
      "files": "<files>"
    },
    "name": "graph_relevant"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoProject directory. A relative path resolves against the MCP server's working directory..
filesYesFiles you are about to change, relative to the repository root
budgetNoToken budget for the answer, 100-20000

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv5.6.0

TDQS

A4.2/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint, openWorldHint=false, destructiveHint=false), the description discloses that results are ordered most-important-first and cut to a token budget, that output is JSON, and that the tool is read-only, local, requires no SKYLOS_API_KEY, has no daily limit, and sends nothing to the cloud. That is materially useful context an agent cannot get from the structured fields.

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?

The first sentence front-loads the purpose, ranking, and per-item payload before moving to the usage trigger. The second paragraph on API-key-free local operation is well placed but slightly expands beyond the core job; overall there is little waste and the structure is easy to scan.

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?

With an output schema present, the description does not need to enumerate return values, and annotations already cover the safety profile, so the added notes on offline operation, budget, and ranking make the definition self-sufficient for invocation. Minor gaps remain on behavior with bad paths or empty results, but nothing an agent needs in order to call it correctly is missing.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3. The description adds meaning beyond the schema by explaining that ranking is by importance and that the answer is truncated to the budget, and that the files listed are the ones the agent is about to change. It does not explain edge cases such as invalid or empty file lists, so 4 rather than 5.

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 specific resource and its selection rule: functions and classes elsewhere in the repo that matter most to the given files, ranked by importance and truncated to a token budget. Each result item is defined (signature, file/line, summary, relation, area), so an agent knows exactly what comes back. It does not name or contrast with siblings such as graph_impact or graph_describe, which keeps it from a 5.

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

Usage Guidelines4/5

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

"Use it before editing to know what else to read" gives a clear, actionable trigger tied to a moment in the agent's workflow. There are no exclusions or named alternatives, so the agent must infer when graph_impact or graph_describe would be the better pick, which keeps this below 5.

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