Skip to main content
Glama

METODIC

by io.metodic
OverviewDiscussionsAdmin

Answer from the Metodic library

answer_from_library
Read-onlyIdempotent

The answer format for anything the user could pick up and use. ALWAYS use this — not generate_document, not prose, not a web search — for a question about WHAT TO USE OR READ — 'which energizer for a flat afternoon group', 'what learning formats could I run this session as', 'which framework fits a two-day programme', 'give me a case for this topic'. MATCH THE TOOL TO WHAT WAS ASKED. Asked which SESSIONS, programmes, formats or examples of sessions ('what could I run for an offsite with 30 people', 'show me examples of sessions like this') → find_session_format, and put the results in the formats field, plus list_my_sessions in my_sessions when they mean their own. Asked which ACTIVITY or working form → search_methods, into methods. Asked which METHODOLOGY → list_frameworks, into framework. Reading → search_articles, into reading. Answering a question about sessions with a list of methods is the wrong answer to the question. First call the matching lookup to see what exists, then call THIS with the few you picked and, for each, WHY it fits this user's situation. Metodic resolves every slug against the real library and renders one branded answer card; anything that does not exist is silently left out. Do not answer such questions in prose and do not dump a search result — a chosen shortlist with reasoning is the whole point. Free.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
caseNoOptional single written case. For several, use cases instead.
noteNoOptional closing caveat or tip.
casesNoOptional written cases to put in front of participants — use THIS when the user asks for more than one ('give me three cases'). Each is a short scenario the group works on. This is where a case belongs; do NOT make a separate document for it.
introYesOne or two sentences framing your answer: what you went for and why.
formatsNoOptional ready-made session formats (slugs from find_session_format).
methodsNoMethods you picked, in the order you'd recommend them.
readingNoOptional reading. Use article_slug for a Metodic article; otherwise give title and author and it is shown as an external work.
questionYesThe user's question, in their own words — becomes the heading.
frameworkNoOptional framework to hang it on.
session_idNoOptional but STRONGLY preferred when the conversation is about a session: saves this answer to that session's Answers tab in Metodic, so it outlives this chat. Pass it whenever you know which session this is about.
my_sessionsNoOptional: the user's own earlier sessions worth reusing (ids from list_my_sessions).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already cover readOnly/idempotent/non-destructive/openWorld=false, but the description adds real behavior: Metodic resolves every slug against the real library, renders one branded answer card, and silently drops anything nonexistent. A silent-drop behavior is exactly the kind of hidden trait an agent needs, though return shape and session-saving are largely delegated to the schema.

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 rule and heavily information-dense, with every routing line doing work. It runs long and contains a couple of restatements ('Answering a question about sessions with a list of methods is the wrong answer' repeats the preceding instruction).

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?

For an 11-parameter aggregator tool with full schema descriptions and no output schema, the description supplies the missing pieces: the lookup-first workflow, routing to siblings, and the rendering/dropping behavior. Nothing an agent needs in order to call it correctly is absent.

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 all 11 parameters are already documented, including the case/cases and slug/why semantics. The description only reinforces the why reasoning quality and the lookup-then-fill workflow, adding little beyond the schema's own field descriptions.

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 function — composing one branded answer card from library picks — and explicitly contrasts itself with generate_document, prose, and web search. The routing sentences naming find_session_format, search_methods, list_frameworks and search_articles make it unmistakable which sibling covers which sub-question.

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

Usage Guidelines5/5

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

Explicit when/when-not plus alternatives: 'ALWAYS use this — not generate_document, not prose, not a web search — for a question about WHAT TO USE OR READ', followed by a decision table mapping question types to the lookup tool to call first. It even warns against the wrong pattern (answering a sessions question with a list of methods).

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

All METODIC toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources