Skip to main content
Glama

agy_discussion_read

Read-onlyIdempotent

Read roles, messages, decisions, memory/budget versions, context manifests, and linked runs for a discussion ID, or list task summaries when ID is omitted; no model call.

Instructions

List task summaries when discussion_id is omitted; otherwise read roles, attributed messages, decisions, memory_versions, budget_versions, context manifests and linked runs. Memory/budget expected version is the history length (0 initially). No model call.

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": "agy_discussion_read"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
discussion_idNo
message_limitNo
message_offsetNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.9.0
    • addedInput schema / properties / message_limit
      Added value: +{
      +  "default": 100,
      +  "title": "Message Limit",
      +  "type": "integer"
      +}
    • addedInput schema / properties / message_offset
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "integer"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Message Offset"
      +}
  2. First observedv0.5.2

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent and closed-world, so safety is covered; the description adds two genuinely new facts: no model call is made (no inference cost) and the expected version for memory/budget equals history length with 0 initially, which is the optimistic-concurrency contract. It does not disclose paging behavior or what happens if a version is stale.

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-loads the mode distinction in the first clause, then packs the returned surface into a compact list, then two short clarifying sentences. Dense but every sentence carries information; the long field enumeration is the only mildly taxing part.

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 the enumerated return fields are somewhat redundant, and the pagination parameters remain undocumented both in schema and description. The version semantics are a valuable addition, but for a 4-parameter dual-mode tool with zero schema coverage, the definition leaves real gaps in how to control result size.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must carry all parameter meaning, and it only explains discussion_id (mode switch) plus the version notion. The three pagination parameters (limit, message_limit, message_offset) — including the non-obvious distinction between limit and message_limit — are never explained anywhere.

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 resource (discussion) and two clearly separated behaviors keyed on discussion_id: a summary listing versus a full detail read enumerating roles, messages, decisions, versions, context manifests and linked runs. The only gap is that it never contrasts itself with siblings like agy_discussion_memory or agy_history, so an agent must infer the boundary from the name.

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?

Explicitly says when to trigger each mode: omit discussion_id to list, supply it to read the full record. That is a clear conditional rule rather than implied usage. It stops short of naming alternatives or exclusions (e.g. when to prefer agy_discussion_memory or agy_history instead).

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