Skip to main content
Glama

read_messages

Read-only

Retrieve retained bridge journal records for a recipient to inspect transport attempts and bridge replies without consuming or acknowledging messages.

Instructions

Read retained bridge journal records for a recipient. Records transport attempts and bridge replies, not every native message or proof of agent receipt. Reading does not consume or acknowledge messages; expired records may be pruned when the journal opens.

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": "read_messages"
  }
}

Input Schema

NameRequiredDescriptionDefault
afterNoOnly return records created after this ISO timestamp.
limitNo
recipientNoFull recipient ID. Codex clients must supply this; other clients default to inferred_sender.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, destructiveHint=false and a closed world, but the description adds substantial context those fields cannot express: reads do not consume or acknowledge, and expired records may be pruned when the journal opens. It also discloses the completeness limit of the data itself. That is exactly the kind of side-effect and data-scope disclosure a read tool needs beyond its annotations.

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 tight sentences, each doing distinct work: resource identity, data-scope caveat, and read side effects. The most important framing (what the journal is) comes first, and there is no filler or redundancy.

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?

For a three-parameter, read-only tool with no output schema, the description covers resource meaning, retention behavior, and non-consuming semantics. It does not explain return shape or whether results are paginated (implied by 'limit'), which would be the last missing piece given the absence of an output schema.

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 67% — 'after' and 'recipient' are documented in the schema, while 'limit' is documented only by default/min/max constraints. The description adds nothing about any parameter, so the schema carries nearly all the semantic load. A 3 reflects adequate but unenriched parameter guidance.

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 description gives a specific verb and resource ('Read retained bridge journal records for a recipient') and sharply bounds the content: transport attempts and bridge replies, 'not every native message or proof of agent receipt.' That boundary makes the tool distinguishable from a generic message reader, but no sibling (list_sessions, message_status, send_message) is named, so routing among siblings still requires inference.

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?

'Reading does not consume or acknowledge messages' implies this is the safe, repeatable way to inspect the journal, which is usable guidance. However, there is no explicit statement of when to use this versus message_status or list_sessions, and no prerequisite conditions are stated. Usage is implied rather than directed.

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