Skip to main content
Glama
Sign In
Agent Guild

Agent Guild

by oddessentials
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Read reply history

read_replies
Read-only

Reads a session's retained replies in order, returning ids and cursors. Pass the last handled cursor as after to continue, or omit it to start from the oldest retained reply.

Instructions

Read retained replies in order, with ids and cursors. Pass your last handled cursor as after; omit it to start at the oldest retained reply. Reads do not consume replies. Check gap for evicted or reset history and save each cursor only after handling its reply.

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": "read_replies"
  }
}

Input Schema

NameRequiredDescriptionDefault
afterNoA cursor returned for this session. Omit on the first read.
limitNoMaximum replies to return, from 1 to 100. Defaults to 20.
session_idYesThe session id from list_sessions.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description still adds real substance on top: reads do not consume replies, the result is ordered, a gap field signals evicted or reset history, and cursors should only be persisted after handling. That is meaningful behavior an agent cannot get from the annotations alone; only return payload details are left unspecified.

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?

Four short sentences, purpose first, then the cursor protocol, then the non-consuming guarantee, then the retention caveat and save discipline. Nothing is redundant and no sentence can be dropped without losing operational meaning.

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, the description carries the burden of describing results and it does name the key return elements (ids, cursors, gap). What a single reply contains is left unstated, so it is strong but not exhaustive.

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 100%, so the baseline would be 3. The description nonetheless adds meaning beyond the schema for the after parameter by identifying it as "your last handled cursor" and clarifying that omission means starting at the oldest retained reply, which is more precise than the schema's "omit on the first read".

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?

"Read retained replies in order, with ids and cursors" gives a specific verb and resource plus two concrete guarantees (ordering, id/cursor exposure). It is clear what the tool returns, though it never explicitly contrasts itself with the singular sibling read_reply, so differentiation is left implicit.

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?

The description states a clear calling pattern: pass your last handled cursor as after, omit it to start at the oldest retained reply. That is actionable usage context. It stops short of naming an alternative tool or stating exclusions, so it lands just below the explicit when/when-not bar.

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