Skip to main content
Glama

Canon Search

canon_search
Read-onlyIdempotent

Search CanonCannon for ideas that recur across podcasts, claims extracted from 10,000+ episodes of 162 tracked shows, each with the MEASUREMENT behind its status: how many independent podcasts and speakers repeat it (excluding whoever originated it) and the bar in force. Use this to tell real cross-show consensus from one author on a book tour. Requires a CanonCannon API key via _apiKey. Example: canon_search({ query: "longevity" }), q is matched as a PHRASE upstream, so prefer one or two words ("zone 2", not "zone 2 training").

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "longevity"
    },
    "name": "canon_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
tierNo"canon" = cleared the independent-spread bar; "observed" = extracted but not cleared. Omitting this returns both.
labelNoFilter to one label, e.g. "Canon", "Curious", "Novel", or an editorial label.
limitNoEntries per page, 1-100. Default 25.
queryNoFree-text search over canon titles, claims and summaries, e.g. "creatine cognition".
cursorNoKeyset cursor from a previous call's next_cursor. Not an offset.
_apiKeyNoCanonCannon API key (cc_live_...). Every /api/v1 endpoint refuses without it. Keys are issued by CanonCannon, https://canoncannon.com

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / _apiKey / description
      Previous value: -"CanonCannon API key (cc_live_...). Every /api/v1 endpoint refuses without it. Keys are issued by CanonCannon — https://canoncannon.com"New value: +"CanonCannon API key (cc_live_...). Every /api/v1 endpoint refuses without it. Keys are issued by CanonCannon, https://canoncannon.com"
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already establish read-only, idempotent, non-destructive behavior, so extra credit goes to the description for disclosing the auth requirement (API key via _apiKey, every endpoint refuses without it) and the measurement model behind each result. It does not cover pagination behavior or result volume, which the cursor/limit params imply but never explain.

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 purpose, then usage rationale, then auth and query-shaping advice. The middle sentence is dense and long, and the `q` versus `query` naming slip costs a point, but nothing is 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?

There is no output schema, and the description compensates by explaining what each entry carries (independent podcast/speaker counts and the bar in force). Auth, query shaping and interpretation are all covered; only result shape and paging behavior are left implicit.

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?

With 100% schema coverage the baseline is 3, but the description adds real operational meaning: queries are matched as a PHRASE upstream, so short one- or two-word queries are preferred. That guidance is absent from the schema. Minor friction: it refers to `q` while the actual parameter is `query`.

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: searching CanonCannon for recurring ideas/claims extracted from 10,000+ episodes across 162 shows. It also defines the distinguishing substance of the corpus (independent-spread counts, excluding the originator, plus the bar in force), which separates it from episode-level siblings like canon_episode_search.

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?

"Use this to tell real cross-show consensus from one author on a book tour" gives a concrete decision rule for when this tool is the right one. It stops short of naming alternatives or when-not-to-use cases, so 4 rather than 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.