Skip to main content
Glama
SVerITG

Metis

by SVerITG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Metis — Get Continuity Context

get_continuity_context

Retrieve prior sessions, decisions, procedures, and library items on a topic before answering, so responses build on existing research instead of starting fresh.

Instructions

Find what the researcher has already done that bears on the current question.

Call this before answering anything substantive, so the reply can be framed in
their own prior work instead of starting from nothing. This is what makes Metis
read as a second brain rather than a fresh chat: "this is your fifth session on
the dashboard since May" is only sayable if something counted.

Returns, where each exists:
  - overall span — recorded sessions, how long Metis has been running, and how
    much is stored (memories, concepts, procedures, papers)
  - this project — age, session count, current next step
  - prior sessions on the same topic, newest first
  - decisions already taken (so a settled question is not reopened)
  - procedures that already cover this (follow them rather than improvising)
  - library items and news threads on the topic
  - the most recent briefing and whether it was read

USE IT HONESTLY. Weave one or two genuine references into the answer; do not
recite the whole payload, and never invent continuity. Empty fields mean there
is nothing to say — say nothing rather than padding. A fabricated link makes
the memory layer feel decorative, which defeats the purpose.

Args:
    topic: The question or subject being worked on. Free text; salient terms
        are extracted for matching.
    project_id: Project slug to scope to (e.g. "metis-dashboard"), if known.
    limit: How many prior sessions to return. Default 4.

Returns:
    A compact readable digest, plus a ready-made one-line continuity summary.

Input Schema

NameRequiredDescriptionDefault
limitNo
topicNo
project_idNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.5

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does so well: it enumerates what the payload contains, explains that topic terms are extracted for matching, gives the default limit, and pre-empts the empty-result case. It never states explicitly that the call is read-only/side-effect-free, which leaves a small gap for a tool with zero annotation coverage.

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?

Purpose and trigger are front-loaded before the payload enumeration and honesty coaching, so scanning works. Some bulk is avoidable: the seven-bullet returns list largely restates the output schema, and the honesty paragraph runs longer than the actual instruction requires.

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 a three-parameter retrieval tool with 0% schema coverage, the description covers arguments, invocation timing, payload composition, and failure semantics; the output schema exists but the digest description still helps the agent decide whether to call it. Nothing material is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% — parameters are bare titles with defaults — so the description must compensate, and it does: topic is described as free text whose salient terms drive matching, project_id gives a concrete slug example, and limit is tied to prior-session count with its default. No parameter meaning is left to guesswork.

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 opening line gives a specific verb and resource — find what the researcher has already done that bears on the current question — and the returns list scopes it further (sessions, decisions, procedures, library items, briefings). It does not, however, name or distinguish itself from close siblings like surface_relevant_context, get_research_context, or load_project_context, so an agent must infer the split.

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?

"Call this before answering anything substantive" is an explicit, actionable trigger, and the honesty paragraph adds a clear negative constraint (don't recite the payload, don't invent continuity, say nothing on empty fields). It stops short of naming alternatives or stating when not to call it in favor of another context tool.

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

Deploy Server

Other Tools