Skip to main content
Glama

Foundry MCP

by com.foundry-mcp
OverviewDiscussionsAdmin

compendium-page-search

Read-onlyIdempotent

Full-text search inside JournalEntry compendium packs — matches page NAMES and page CONTENT. This is the tool for rules/lore text questions: compendium-search only sees document names in pack indexes, so rule pages, spell lists, and class write-ups are invisible to it. Requires bridge module 8.11.0+.

WHEN TO USE

  • "What does the grappled condition say?" → query: "grappled", pageTypes: ["rule"]

  • Find a class/subclass rules page, a spell list page, or any lore text

  • Locate which journal a phrase appears in

WORKFLOW

  • Each match carries the PAGE uuid — pass it to uuid-resolve for the full page text.

  • matchedIn tells what matched; name matches win (content is not scanned then) and their snippet is always null.

  • Content matches include a ~200-char plain-text snippet around the first hit.

SEMANTICS

  • Query is a case-insensitive substring.

  • Packs are scanned lazily in order until limit is reached; results are in scan order, unsorted.

  • Explicit unknown packIds error with "Pack not found: "; non-journal packs with "Compendium pack is not an JournalEntry pack: ".

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMax matches, default 25. Scanning stops once reached.
queryYesSubstring to find, case-insensitive. Matched against page names and (by default) page text content.
packIdsNoRestrict to specific JournalEntry packs. Omit to search ALL journal packs in the world.
pageTypesNoPage subtypes to include, e.g. ["rule"], ["spells"], ["class","subclass"], ["text"]. Omit for all types.
searchContentNoDefault true. Set false to match page NAMES only — much cheaper; use it when the page title is known.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A5/5.0
Behavior5/5

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

While annotations already indicate read-only, idempotent, and non-destructive behavior, the description adds rich behavioral details: name matches win and skip content scanning, content matches include ~200-char snippets, packs are scanned lazily in order and results are unsorted, and specific error messages for unknown or non-journal packs. This goes well beyond the annotations.

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?

The description is well-structured with clear sections (main purpose, WHEN TO USE, WORKFLOW, SEMANTICS) and is front-loaded with the core purpose. Every sentence adds value; there is no fluff or redundancy.

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 the tool's complexity (5 parameters, no output schema), the description provides everything an agent needs: how to construct queries, interpret results (page uuid, matchedIn, snippet), handle ordering, and understand error conditions. It also references the uuid-resolve workflow for retrieving full text. Nothing essential is missing.

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

Parameters5/5

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

The input schema already has 100% description coverage, but the tool description adds extra semantics not in the schema: case-insensitive substring behavior, default limit of 25, lazy scan order, the meaning of matchedIn and snippet behavior, and error handling for packIds. It enriches each parameter's meaning beyond the schema.

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 clearly states it performs full-text search inside JournalEntry compendium packs, matching page names and content. It distinguishes itself from compendium-search, which only sees document names, making its unique purpose unambiguous.

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 includes a dedicated WHEN TO USE section with concrete examples (e.g., 'grappled condition' → query 'grappled', pageTypes ['rule']) and explicitly names the alternative compendium-search and why this tool is preferred for page-level content. It also explains when to use searchContent=false and how to chain with uuid-resolve.

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

All Foundry MCP toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources