Skip to main content
Glama

cd_watch

cd_watch
Read-only

Track changes in Chief Delphi forum listings across calls: get new topics and post/view count deltas for ongoing discussions without rereading the same listings.

Instructions

Report what changed in a Chief Delphi listing since the previous cd_watch call on the same scope: brand-new topics, plus topics whose post or view counts moved, with deltas. The first call records a baseline and lists nothing new; call it again later to get the diff. Made for following an ongoing discussion — game rumor and prediction threads during a season, a build thread you are tracking, or one category during kickoff week — without re-reading the same listings. State persists in .state/ (separate from the disposable cache), is keyed per scope, and reset starts over.

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": "cd_watch"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoListing to diff. Default "latest" (best for watching); "top" also works.
limitNoRows per section. Default 25.
orderNoListing sort. Defaults to the feed order.
resetNoDiscard the stored baseline first, so this call becomes the new starting point. Default false.
periodNoFor mode=top. Default "daily".
categoryNoCategory id/slug to watch. Omit for the whole forum.
max_charsNoCap the reply at this many characters (default 20000).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare readOnly and openWorld; the description adds important behavior beyond that: first call returns nothing new, state persists in .state/ (separate from disposable cache), state is keyed per scope, and reset discards the baseline. These details are essential to avoid misinterpreting an empty first response as an 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-loads the core diff behavior and keeps the baseline explanation early. It is somewhat long but every sentence provides useful context; minor tightening could improve it, but no sentence is wasted.

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

Completeness5/5

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

Given no output schema, the description adequately explains the return shape (new topics plus topics with moved counts and deltas) and the stateful baseline behavior. An agent has enough information to call it correctly, including the first-call edge case and reset semantics.

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 schema already defines mode, order, reset, period, category, limit, and max_chars. The description adds semantic context by explaining that state is keyed per scope, which implies changing category/mode/order creates a separate baseline, and it clarifies reset behavior beyond the schema's brief note.

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?

States a specific verb and resource ('Report what changed in a Chief Delphi listing') plus the exact diff semantics: new topics and moved post/view counts with deltas. This clearly distinguishes it from sibling listing tools like cd_topics or cd_topic, which do not diff against prior calls.

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?

Explicitly says when to use it (following ongoing discussion, rumor/prediction threads, build threads, kickoff week) and when not to (instead of 're-reading the same listings'). It also explains the two-call pattern: first call establishes baseline, later calls produce the diff, and reset starts over.

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