Skip to main content
Glama

cd_find

cd_find
Read-only

Find Chief Delphi forum topics by keywords, scanning topic listings and checking thread bodies to confirm matches within the selected window.

Instructions

Find Chief Delphi topics matching keywords. Chief Delphi robots.txt disallows /search, so this does NOT call the forum search API: it pulls topic listings (mode/period/category/page window), matches tokens against titles, tags and excerpts, ranks the hits, then fetches /raw for the top with_body candidates to confirm the phrase inside the thread and report which posts matched. Coverage is the listing window you ask for, so the default mode=auto pools both most-engaged (top) and most-recent (latest) topics. An empty result means "not in this window", not "the forum has no such thread" — widen pages= or change mode. Good targets: game rumor/prediction threads, rule clarifications, strategy and build threads, event discussion.

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": {
      "query": "<query>"
    },
    "name": "cd_find"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoListing pool to search. Default "auto" (top + latest merged).
limitNoResults to print. Default 12.
matchNoRequire every token (all, default) or at least one (any).
orderNoSort order for the listing pool when mode is latest/new.
pagesNoListing pages pooled (30 topics each). Default 4 (2 top + 2 latest); 40 ≈ 1200 topics and ~15s.
queryYesKeywords, e.g. "canopy game announcement" or "hub latency".
periodNoPeriod for the top part of the pool. Default "yearly"; use "all" for oldest-and-largest, "monthly" for this month.
categoryNoRestrict to one category id/slug (see cd_categories).
max_charsNoCap the reply at this many characters (default 20000).
with_bodyNoFetch /raw and confirm the match inside the thread for this many top candidates. Default 8; 0 skips body checks.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior3/5

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

The annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered; the description adds genuine context by disclosing the internal flow (listing pool match, ranking, /raw confirmation for with_body candidates) and coverage semantics. It also notes the ~15s cost at pages=40, which is useful operational context. However, it doesn't describe the shape of the returned results (what a hit looks like, whether excerpts or post ids come back), leaving some behavioral opacity.

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-loaded with the core verb and the reason for the non-obvious implementation, then the coverage caveat and targets. Dense but every sentence carries information; the one weakness is that parameter-level behavior and usage guidance are interleaved in a single long paragraph rather than structured.

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 10-parameter, no-output-schema tool, it covers mechanism, coverage limits, empty-result semantics, and performance cost — enough for correct invocation. The remaining gap is the return format: with_body and limit/max_chars interact to shape output, but the description doesn't say what a result entry contains.

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 100%, so baseline is 3. The description clarifies the pool semantics (mode=auto merges top and latest, pages is the coverage window) and what with_body actually does (fetch /raw to confirm the phrase inside the thread), which adds meaning beyond the schema's per-field text. It still doesn't clarify interactions such as how order applies in auto mode or how max_chars affects truncation of ranked hits.

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 ("Find Chief Delphi topics matching keywords") and immediately scopes it: it does not use the forum search API but matches tokens against titles, tags and excerpts from listings. This distinguishes it clearly from plain listing tools such as cd_topics or cd_raw.

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?

Gives concrete when-to-use targets (game rumor/prediction threads, rule clarifications, strategy/build threads, event discussion) and explains the critical interpretation rule that an empty result means "not in this window" with remediation via pages= or mode. It falls short of a 5 because it never explicitly contrasts against sibling tools (e.g., when to use cd_topics or cd_raw instead).

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