Skip to main content
Glama

trail

Walk a work thread back in time to see each event—opens, decisions, constraints, evidence, and closes—so you can reconstruct how it reached its current state when resume shows only where it is now.

Instructions

Walk one thread back in time, one line per event: opened, focus/open/next declarations (with owner), decisions, constraints, ruled-outs, notes, evidence, commits, closed. The most recent limit lines; pass before=<the earliest line's at> for older ones. Use it when you need how a thread got where it is — resume gives only where it is now. Notes are marked interpretation, not evidence. inspect(ref) for any line in full.

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": {
      "case_id": "<case_id>"
    },
    "name": "trail"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
beforeNo
case_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the full load and does well: it discloses ordering ('most recent `limit` lines'), the shape of each line, and a meaningful semantic caveat that notes are interpretation rather than evidence, which affects how an agent should weigh output. It stops short of stating that this is a non-mutating read and says nothing about error behavior when a case or thread is absent.

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?

Roughly four sentences, front-loaded with what the output looks like before any caveats or alternatives. Every sentence carries information, but the delivery is telegraphic in places ('inspect(ref) for any line in full'), and the long enumerative clause of event types is dense enough to slow parsing.

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, annotation-free, output-schema-free read tool, the description covers ordering, line composition, pagination, and the escalation path to `inspect`. The remaining gaps are modest: no statement of the required `case_id`'s role and no note on what happens with an empty or unknown thread.

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 description coverage is 0%, so the description must compensate, and it explains both optional parameters: `limit` as the count of most recent lines and `before` as a cursor taking the earliest line's `at` value, which also implies the lines carry an `at` field. It never explicitly states that `case_id` selects the thread being walked, leaving the required parameter to inference from the tool framing.

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?

A specific verb plus resource ('walk one thread back in time') is immediately followed by the exact content of a line: opened, declarations with owner, decisions, constraints, ruled-outs, notes, evidence, commits, closed. The final clause explicitly separates it from `resume`, which only shows current state, so an agent can distinguish the two without opening either schema.

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

Usage Guidelines5/5

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

The description gives an explicit use condition ('when you need how a thread got where it is') and names the alternative with the reason to reject it ('resume gives only where it is now'). It also documents the pagination path for going further back via `before`, so the agent knows how to continue rather than stopping at the limit.

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