Skip to main content
Glama

list_sessions

Lists past AI coding sessions with titles, dates, sources, and projects, returning the session IDs needed to retrieve full conversation details. Filter by source or project path.

Instructions

List available past sessions with their titles, dates, sources and projects.

source: "all" or one of claude, codex, gemini, opencode, cursor. project: optional repository path filter. Returns session IDs needed for get_session.

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": "list_sessions"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
sourceNoall
projectNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It does disclose what is returned (titles, dates, sources, projects, session IDs) and the accepted source values, but says nothing about ordering, pagination, or the default limit of 50, and only implies that the operation is a read.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short lines with zero filler: the purpose leads, the per-parameter notes follow, and the get_session link closes. The label-style formatting for source/project is efficient rather than cryptic.

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

Completeness3/5

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

An output schema exists, so return values need not be described in depth, and the description correctly covers the two semantically ambiguous parameters. However, for a zero-annotation tool with 0% schema coverage, leaving 'limit' entirely undocumented and omitting any note on result ordering or volume leaves a real gap.

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 0%, so the description must compensate. It does well on two parameters, spelling out the accepted 'source' values (claude, codex, gemini, opencode, cursor, all) that the schema leaves as a bare string, and explaining 'project' as a repository path filter, but 'limit' is never mentioned despite being the only control over result size.

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 verb and resource ('List available past sessions') and names the fields returned (titles, dates, sources, projects). It also ties itself to the sibling 'get_session' by noting it returns the IDs that tool needs, which distinguishes it from the analysis/recall siblings, though it does not explicitly rule out search_history or session_recall.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: an agent can infer it should call this to enumerate sessions and obtain IDs for get_session. There is no explicit when-not guidance and no comparison against search_history or session_recall, so the agent must guess whether listing or searching is appropriate.

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