Skip to main content
Glama

Find steering files

find_steering_files
Read-onlyIdempotent

Discovers agent steering files under an allowed folder and groups them by load trigger—every session, on match, on invocation, on demand, or memory—so you know which instructions apply.

Instructions

Discover agent steering files under the allowed folder (CLAUDE.md, AGENTS.md, GEMINI.md, .claude/skills//SKILL.md, .claude/agents, .claude/commands, .claude/rules, .cursor/rules/.mdc, .cursorrules, .windsurf rules, .clinerules, .github/copilot-instructions.md, *.instructions.md, *.prompt.md, memory files) and group them by when they load: every session, on match, on invocation, on demand, memory. Symlinks are not followed.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "find_steering_files"
  }
}

Input Schema

NameRequiredDescriptionDefault
max_depthNoFolder depth to search (default and max 12)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

The annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavior: the search is bounded to an allowed folder, symlinks are not followed, and results are partitioned into five specific load phases. It does not discuss depth defaults or pagination, which are handled in schema/full results.

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?

A single front-loaded sentence led by the verb, with the file-pattern enumeration followed by the grouping behavior. The long parenthetical list is dense but each entry earns its place by defining scope. No filler or redundant restatement of the title.

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 read-only discovery tool with no output schema, the description does the important work: it defines exactly which files are found and describes the shape of the result (grouped by load phase). The only omission is any indication of what the per-file entry contains, which is a minor gap given the simplicity of the tool.

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% for the single max_depth parameter, including its default and max of 12, so the schema carries the semantics. The description adds nothing about depth or its interaction with the allowed folder. With high schema coverage the baseline of 3 is appropriate.

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 opens with a specific verb and resource ('Discover agent steering files') and then enumerates the exact file patterns covered, so an agent knows precisely what this returns. The second clause adds the grouping behavior by load phase, which further distinguishes it from lint_steering and suggest_fixes. It stops short of naming a sibling explicitly, so a 4 rather than 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 Guidelines3/5

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

Usage is implied by the scope statement ('under the allowed folder'), so an agent can infer this is the discovery step before linting or loading. There is no explicit when-to-use/when-not statement and no routing to alternatives such as lint_steering or load_plan. Minimum-viable guidance only.

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