Skip to main content
Glama

Read Tofu’s guide

getGuide
Read-onlyIdempotent

Read Tofu’s guide, one section at a time: the skill that comes with Tofu’s plugin, on checking, deploying and running apps with these tools. With no section, it lists every section by title, anchor, heading level and size in words. With section set to an anchor from that list, it returns that section’s text, up to words words (1,200 by default, 6,000 at most), with the sections and numbered steps inside it; truncated: true with a note means the rest was not returned. Making a mobile web app (a PWA, from Tofu’s pwa-v1 starter) is make-a-mobile-web-app, and reading the mobile metadata Tofu observes is mobile-metadata-observations. It reads only text built into this server and changes nothing.

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": "getGuide"
  }
}

Input Schema

NameRequiredDescriptionDefault
wordsNoThe most words of the section to return: 1,200 when left out, 6,000 at most.
sectionNoAn anchor from the list this tool returns with no `section`, such as `make-a-mobile-web-app`. Left out, the answer is that list.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already establish readOnly/destructive/idempotent/openWorld behavior, yet the description still adds real value: truncation is disclosed with the exact signal (`truncated: true` plus a `note`) and the default/maximum word budgets. "Reads only text built into this server and changes nothing" largely restates existing hints, so it is not fully additive.

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 core action, then layered list-mode, read-mode, truncation, and topic anchors in a logical order; every sentence carries information. It is a single dense paragraph, and the closing "reads only text ... changes nothing" is redundant with the annotations.

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

Completeness5/5

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

There is no output schema, and the description compensates fully by describing both return shapes (section list fields, and section text with nested `sections`/numbered `steps`) plus the truncation contract. For a two-optional-parameter read tool, an agent has everything needed to call it and interpret results.

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%, so the schema already documents both `words` and `section`, including defaults, bounds and the omitted-section behavior. The description adds meaning at the payload level (what a section list contains: title, anchor, level, word count) but little that the schema does not already carry about the parameters themselves.

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?

States a specific verb+resource ("Read Tofu's guide, one section at a time") and immediately scopes what the guide covers ("checking, deploying and running apps with these tools"). It is clearly distinguishable from siblings like getBuildLogs or databaseBackups, which serve different resources.

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?

Gives an explicit two-mode workflow: omit `section` to get the list of sections, then pass an anchor from that list to read the section. It further routes the agent by naming the exact anchors for two tasks (`make-a-mobile-web-app` and `mobile-metadata-observations`). No explicit when-not-to-use or alternative-tool exclusion is offered, which keeps it below a 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources