Skip to main content
Glama

canton-ccpedia

by io.github.UnityNodes
OverviewDiscussionsAdmin

search_dev_fund

Read-onlyIdempotent

Search ALL Canton Dev Fund text for words: proposal files, PR descriptions, every comment, formal review and inline review comment, ranked by relevance with a snippet around the match. Scope can be narrowed to comments, proposal_files or descriptions, and to one GitHub author. Use for "who said what about X", "which proposals mention Y", "did a reviewer object to Z". Default mode "words" is lexical (the words must appear, exact and exhaustive). Mode "meaning" searches the same text by meaning with embeddings plus words, so "did anyone worry about validator uptime" finds a comment that never says uptime; it cannot be limited to one author. For a ranked pick among whole proposals for an idea use find_rfp_for_idea or detect_builder_overlap. Canton-specific.

Input Schema

NameRequiredDescriptionDefault
modeNowords (default): exact, exhaustive, every word must appear. meaning: best match by meaning and words together, over comments, proposal files and PR descriptions; does not support the author filter.words
limitNoHow many hits to return. Default 10, max 30.
queryYesWords to look for, e.g. "indexer champion" or "volatility amendment". In mode "meaning", a plain-language question or phrase.
scopeNoall, comments (comments + reviews + inline review comments), proposal_files, or descriptions (titles and descriptions of pull requests and tracking issues).all
authorNoGitHub login; limits comments and PR descriptions to that person.
offsetNoSkip this many hits, for paging.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. Changed2 schema fields changed
    • addedInput schema / properties / mode
      Added value: +{
+  "default": "words",
+  "description": "words (default): exact, exhaustive, every word must appear. meaning: best match by meaning and words together, over comments, proposal files and PR descriptions; does not support the author filter.",
+  "enum": [
+    "words",
+    "meaning"
+  ],
+  "type": "string"
+}
    • changedInput schema / properties / query / description
      Previous value: -"Words to look for, e.g. \"indexer champion\" or \"volatility amendment\"."New value: +"Words to look for, e.g. \"indexer champion\" or \"volatility amendment\". In mode \"meaning\", a plain-language question or phrase."
  3. Added

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive and closed-world, so the safety profile is covered. The description adds real behavioral context beyond that: mode 'words' is exact and exhaustive (every word must appear), while 'meaning' uses embeddings plus words and cannot be limited to one author. It stops short of detailing pagination behavior, but the mode semantics are the important disclosure.

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?

It is dense but front-loads the core action and scope before modes and alternatives, and every sentence carries routing or behavioral value. Slightly long, but the information density justifies most of it with little filler.

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?

With no output schema, the description carries the return-value burden and does so ('ranked by relevance with a snippet around the match'). Combined with the mode/scope/author semantics, an agent has everything needed to invoke this correctly.

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 baseline is 3. However the description meaningfully explains the mode enum's behavioral difference and the cross-parameter constraint that 'meaning' mode cannot be limited to one author, information that complements rather than merely restates 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 opens with a specific verb (search) and a precisely scoped resource (ALL Canton Dev Fund text: proposal files, PR descriptions, comments, formal and inline reviews), plus the return shape (ranked by relevance with a snippet). It is clearly distinguishable from generic siblings like search, semantic_search, and search_github_issues.

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 gives explicit trigger questions ('who said what about X', 'which proposals mention Y', 'did a reviewer object to Z') and routes the agent elsewhere for a different need: 'For a ranked pick among whole proposals for an idea use find_rfp_for_idea or detect_builder_overlap.' It also distinguishes the two modes by the question type each answers.

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

All canton-ccpedia 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