Skip to main content
Glama

What the agent loads

load_plan
Read-onlyIdempotent

Shows which markdown files coding agents load at session start, later reads, or never read, including token totals and per-tool cut limits.

Instructions

What each agent (Claude Code, Codex, Gemini CLI, Cursor, Copilot) loads when a session starts in a folder, in order: files at launch with @imports, files that load later (subfolder instruction files on first read, rules on matching files, nested skills), what gets cut (Codex 32 KiB chain, Claude Code 40,000-character on-demand cut, MEMORY.md 200 lines), what is never read and why, and token totals. Each step says whether it rests on vendor docs, a canary run or an assumption. Local estimates, read-only.

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": "load_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
cwdNoFolder the session starts in, relative to the allowed folder (default: the allowed folder itself)
toolNoOne tool; omit for all five
offsetNoSkip this many steps per tool (paging; 60 are listed per call)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already cover read-only, idempotent, non-destructive and closed-world, so the bar is lower. The description still adds valuable disclosure: every step is labeled as resting on vendor docs, a canary run, or an assumption, results are explicitly 'local estimates', and the concrete cutoffs (32 KiB chain, 40,000-character cut, 200 lines) set expectations about precision.

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-loads the resource and then packs the return contents into a single ordered sentence with no filler. It is dense but every clause maps to real report content; a light structural break for the enumeration would help scanning.

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 no output schema, the description must convey what comes back, and it does: ordered steps, deferred loads, truncation limits, never-read items with reasons, provenance labels, and token totals. The per-step record shape is left implicit, but the substantive coverage is strong for a read-only reporting 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 coverage is 100%, so cwd, tool enum, and offset paging are already fully documented in the schema. The description only adds that omitting the tool covers all five agents, which is already implied by the enum documentation. Baseline 3 applies when the schema carries parameter meaning.

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?

States a specific resource (what each agent loads at session start in a folder) and enumerates the vendors covered, so an agent knows exactly what the report contains. It does not name or differentiate itself from siblings such as context_budget, which likely covers overlapping token-budget ground, leaving the boundary to inference.

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?

Implies the triggering context clearly ('when a session starts in a folder') and the tool selection mechanism ('omit for all five'), plus a paging note. There are no explicit exclusions or alternatives offered, so an agent must guess when context_budget would be the better choice.

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