Skip to main content
Glama

cd_topic

cd_topic
Read-only

Read Chief Delphi threads with per-post metadata and paginated windows, then jump to exact posts or pages and choose text or JSON output for structured analysis.

Instructions

Read a Chief Delphi thread with per-post metadata: author, user title, timestamp, like count, which post is replied to, post id, deleted/hidden flags. Threads render in ~20-post windows; jump with at_post= (exact, gap-safe) or page= (page 2 starts at post 21). Discourse pads a window to ~20 live posts, so a thread containing deleted posts can repeat one boundary post between consecutive pages — prefer at_post for exact continuation. Use format="json" to reason over structured fields, format="text" (default) to read the discussion. For a cheap bulk read of a long thread use cd_raw instead.

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": {
      "topic": "<topic>"
    },
    "name": "cd_topic"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoOne-based 20-post page within the thread. Default 1.
chunkNoPosts per window used to compute page (default 20; ignored when at_post is set).
topicYesNumeric topic id from cd_find / cd_topics.
formatNoOutput shape. Default "text".
at_postNoStart the window at this post number. Overrides page.
max_charsNoCap the reply at this many characters (default 20000).
max_postsNoPosts to render from this window. Default 20.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantially more — ~20-post render windows, boundary-post repetition when deleted posts pad a window, and the at_post/page override relationship. The main missing piece is any note on failure modes (e.g. invalid topic id) or rate limits, which keeps it from a 5.

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?

Purpose and scope are front-loaded in the first clause, followed by paging mechanics and then the alternative tool. Every sentence carries operational information — the deleted-post padding caveat in particular prevents a real agent error — with no filler.

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 does the work of explaining both output shapes (structured json fields vs. readable text) and the paging model. It is nearly complete for a 7-parameter read tool, though it omits what happens on an invalid or private topic.

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 already 100%, so the baseline is 3, but the description genuinely adds meaning: at_post is exact and gap-safe and overrides page, page 2 begins at post 21, and chunk feeds the page computation. max_chars and max_posts are left to the schema, which is acceptable given full coverage.

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?

The description opens with a specific verb and resource — "Read a Chief Delphi thread" — and immediately enumerates the per-post fields returned (author, user title, timestamp, like count, reply target, post id, deleted/hidden flags). That level of detail lets an agent distinguish this from cd_raw and cd_topics without opening any 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?

It explicitly routes the agent: prefer at_post over page for exact continuation, and use cd_raw for a cheap bulk read of a long thread. It also states when to choose format="json" versus the default text. Both alternatives and selection conditions are spelled out rather than implied.

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