Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
inspect_projectA

Scan a project and report what would be submitted: detected languages, candidate files with their usable line counts, and every skipped file with the reason. Call this first to see whether the project has enough material and to understand what was excluded.

estimate_materialB

Estimate how the selected files would be split into identifying material, without rendering. Reports the front and back page counts and warns when an exact 30+30 split is not reachable.

generate_materialsB

Generate the source-code PDF, the application form values and a verification report into an output directory. Returns ok=false with the blocking reasons when the material must not be submitted. Pages are drawn from whichever files contain the least Chinese; set drop_cjk=true to also delete Chinese-only lines, which alters the source and is therefore off by default.

check_fieldsA

Validate application form values against the published rules without generating anything. Use this to fix fields before a long generation run.

check_environmentA

Report whether this machine can produce material: Python version, PDF library, PDF reader, fonts and whether the output directory is writable. Call this before a long generation on an unfamiliar machine.

review_manualA

Check a manual outline against the required structure before writing it out: the six chapters in order, FAQ and glossary last, a reason and evidence for any project-specific chapter, and continuous figure numbering. Returns the problems found and the page budget.

explain_rulesA

Return the layout rules and their authority, so the answer to 'why 50 lines' or 'why is the page number top right' is traceable.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.8/5.0

Scored across 7 tools

Disambiguation4/5

The tools map to distinct pipeline stages: environment check, project inspection, field validation, estimation, generation, manual review, and rules explanation. The main pair that could be confused is inspect_project and estimate_material, since both are non-generating analyses, but the descriptions clarify that one scans candidate files and the other models the page split.

Naming Consistency5/5

Every tool follows the same snake_case verb_noun convention (inspect_project, check_fields, generate_materials, etc.). Deviation is minimal—only generate_materials uses a plural noun, which is still predictable.

Tool Count5/5

Seven tools is well-scoped for a specialized submission-generation workflow. Each tool covers a clear phase (preflight checks, validation, estimation, generation, review, rule lookup) and none feels redundant.

Completeness4/5

The lifecycle is largely covered: environment and project preflight, field validation, page estimation, generation with verification report, manual structure review, and traceable rules. Minor gaps exist, such as no tool for authoring or editing the manual/form content itself, but the core workflow has no dead ends.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues