Skip to main content
Glama

list_registry_entries

Idempotent

Enumerate every entry in the unified indicator registry, including verified and unverified rows, with pagination controls for browsing the full catalog.

Instructions

Enumerate the WHOLE unified indicator registry — verified AND not.

The registration-surface enumeration channel (tiered browsing sync, e.g. the public indicator catalog): every registered entry, each carrying its authoritative verified flag (true = directly readable caliber, false = registered/on-demand caliber). This is deliberately PARALLEL to the catalog: list_concepts / ai_search / read keep their verified gate untouched — unverified entries stay out of the catalog, search and every read channel, and this tool does not change that.

Paginated like list_concepts: rows ordered by (source_db, native_code), limit clamped to 1..1000; page with increasing offset until a page comes back shorter than limit — that enumerates the full registry (57k+ entries at ~1000/page).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

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

Input Schema

NameRequiredDescriptionDefault
limitNopage size, 1..1000 (default 500)
scopeNooptional named retrieval scope (see scope_list). This tool is cross-source, so the scope's allow-lists filter the returned rows (source_db above all — 「源即 scope」); the response then names the scope that governed it, so a scope-emptied page is distinguishable from true absence. An unknown scope is an explicit ``unknown_scope`` error, never an empty result.
offsetNorows to skip (default 0)
statusNoNone = all entries (default); "verified" = only the verified subset; "registered" = only the not-verified subset (never-yet- reviewed rows count as registered). Any other value is an explicit ``invalid_status`` error.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior3/5

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

Beyond the annotations it discloses scale (57k+ entries), ordering by (source_db, native_code), limit clamping, and the pagination termination rule (stop at a short page) — genuinely useful behavior not derivable from structured fields. However, it never explains the readOnlyHint=false annotation on what reads as a pure enumeration tool, leaving a real ambiguity about side effects (the phrase 'tiered browsing sync' hints at work being done but is not clarified).

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 scope statement, then pagination mechanics, then scale — a sensible order. Some prose is heavier than needed (backticked terms, the 'deliberately PARALLEL' emphasis repeated across two sentences), but nothing is redundant enough to waste a reader's time.

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?

Output schema exists, so return values need not be explained, and the description covers routing, paging, ordering and the catalog-side-effect boundary. The remaining gap is behavioral around the non-read-only annotation and cost of a full 57k-page walk, which is only implied by the page-count arithmetic.

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, but the description adds meaning the schema does not: the sort key applied to offset/limit paging and the concrete protocol for advancing offset. It does not elaborate the status or scope parameters here, but those are already well documented in 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?

States a specific verb and resource with explicit scope: 'Enumerate the WHOLE unified indicator registry — verified AND not.' It immediately distinguishes the tool from list_concepts/ai_search/read by declaring itself a deliberately PARALLEL registration-surface channel that does not touch the verified gate, so an agent can route between them without opening a schema.

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?

The description gives clear routing context: use this when you need every registered entry including unverified ones, while list_concepts, ai_search and read remain verified-only. It lacks an explicit 'do not use this for X' imperative or a statement about when the enumerated output should feed downstream tools, so it falls short of full when/when-not guidance.

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