Skip to main content
Glama

Typebar (formerly SuperDocs)

list_session_documents

Returns the editable documents open in this session (focused first), each with its id, chunk count, and focused flag — so a client can render document tabs. The response is token-light by default; pass include_html=true to also get each document's reassembled HTML.

ID MAPPING: document_id is the SESSION-LOCAL slot id ("doc_primary", "doc_ab12…"); durable_document_id is the PERMANENT document id (a UUID) — the SAME id list_documents (Files) shows and get_document_detail / rename_document / archive_document / open_documents take (null until the document's first save). focus_session_document, close_session_document, and chat's document_id accept EITHER form, so you can drive a session entirely with durable ids.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "session_id": "<session_id>"
    },
    "name": "list_session_documents"
  }
}

Input Schema

NameRequiredDescriptionDefault
session_idYes
include_htmlNoInclude each document's full reassembled HTML body. Default false (token-light — recommended for AI agents enumerating or switching tabs): returns only ids, title, section count, focused flag, and page setup, omitting the body which can be hundreds of KB per document. The web app passes true to render document content.
report_changedNoResume awareness: when true, each doc carries `changed_since_seen` = its committed version is newer than the version THIS session last saw (changed by another session while away). The web UI sets this ONLY on resume / a chat switch (never on the ~2s poll) so it can show a one-time 'changed since you were last here' notice — ongoing changes are surfaced through the normal change feed. Computed before the roster updates the version this session has seen.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

No annotations are provided, so the description carries the full burden and does so: it discloses the default token-light response shape, the potentially huge cost of include_html ('hundreds of KB per document'), and the pre-update timing semantics of changed_since_seen. It also flags that durable_document_id is null until first save, which preempts a likely agent error.

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 return shape, then costs, then id mapping — good ordering with no filler. The ID MAPPING block is dense but every clause is load-bearing for choosing between id forms; slight over-density in the report/observation of siblings keeps it from a 5.

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

Completeness4/5

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

With no output schema and no annotations, the description does the work: it lists the returned fields in both modes and explains the changed_since_seen flag. What's missing is only the provenance of session_id and any note on ordering guarantees beyond 'focused first'.

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

Parameters4/5

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

Schema coverage is 67% and the description adds real meaning on top: it explains why include_html is off by default and what report_changed computes. It also defines the two id forms used across the tool family, which is the highest-value semantic detail here. The gap is session_id — neither schema nor description says where it comes from (presumably init_session/list_sessions).

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?

Opens with a specific verb+resource+scope: 'Returns the editable documents open in this session (focused first)', and enumerates returned fields (id, chunk count, focused flag). The ID MAPPING paragraph distinguishes it from list_documents (Files) by pointing out which id form each exposes, so an agent can tell the two roster tools apart.

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 concrete selection guidance inside the description: use default mode for 'AI agents enumerating or switching tabs', pass include_html=true only when document bodies are needed, and set report_changed only on resume/chat switch (explicitly 'never on the ~2s poll'). The alternative list_documents is named in the ID mapping but the description never states the selection rule in one place (e.g., 'use this for open session docs, list_documents for all files').

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.