Skip to main content
Glama

pronto-stream

by io.github.nmxmxh

scope_signals

Read-onlyIdempotent

Select a slice of the live wire by facet tags — the structured metadata each signal carries, not the words in its text. Use this when you can name the slice you want: every high-severity climate signal in Japan, everything from one provider, everything in one language. It returns the whole slice whatever words the signals happen to use, which is what separates it from search_signals; reach for search when you have a subject word and no category to name.

Facets cover language, country, region, domain, topic, severity, provider, coverage, and place. Facets that share a key combine with OR. Facets with different keys combine with AND. The filter "country:JP,country:CL domain:climate" selects Japan or Chile, and climate. A locale filter alone cannot answer this question.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum signals to return (default 25, max 200)
cursorNoPage token from META cursor: of the previous response. Omit for the first page.
filterNoFacet expression: space- or comma-separated key:value pairs. Keys are fixed vocabulary — lang, country, region, domain, topic, severity, provider, coverage, place. Same key = OR, different keys = AND. Examples: "country:jp domain:climate" (Japanese climate signals), "country:us,country:cl severity:high" (US or Chile, high severity), "place:Tokyo" (resolved to a gazetteer id). Call list_facets for live values.
relateNoAlso return the link graph over the rows in this response, as REL lines, so repeats of one story can be collapsed without a second call. Off by default.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed4 schema fields changed
    • addedInput schema / properties / cursor
      Added value: +{
+  "description": "Page token from META cursor: of the previous response. Omit for the first page.",
+  "type": "string"
+}
    • changedInput schema / properties / filter / description
      Previous value: -"Facet expression, e.g. \"country:JP domain:climate severity:high\". Call list_facets to see live values."New value: +"Facet expression: space- or comma-separated key:value pairs. Keys are fixed vocabulary — lang, country, region, domain, topic, severity, provider, coverage, place. Same key = OR, different keys = AND. Examples: \"country:jp domain:climate\" (Japanese climate signals), \"country:us,country:cl severity:high\" (US or Chile, high severity), \"place:Tokyo\" (resolved to a gazetteer id). Call list_facets for live values."
    • addedInput schema / properties / filter / examples
      Added value: +[
+  "country:jp domain:climate",
+  "severity:high,critical domain:security",
+  "provider:usgs"
+]
    • addedInput schema / properties / filter / pattern
      Added value: +"^([a-z]+:[^ ,]+([ ,]+|$))+$"
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

The annotations already signal read-only, open-world, and idempotent behavior, and the description adds meaningful behavior beyond those: it explains OR-combination within a orig key and AND-across keys, and makes clear that the tool returns the entire slice regardless of words used by member reasing. It covers the key non-obvious semantics of the tool, though the lack of an output schema means some response-shape behavior is still implicit.

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?

The structure is well front-loaded: a direct verb-first sentence, then usage conditions, then operates behavior and a sample expression. It does repeat some schema content in the prose, so it is slightly longer than the ideal, but no sentence is false or 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?

For a read-only filter tool with complex filter grammer, the description covers when to use it, how to build filters, how it differs from search, and whet sort of slices are supported. The main gap is that hardware it has no output schema and the description does not say what the returned signal objects look like; given the open-world and read-only contexts, however, this doesn't prevent correct intonation.

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?

The input schemas already describes filter thoroughly with grammar, OR/AND rules, examples, and a pointer to list_facets, and it covers limit, cursor, and relate as well. The description repeats the OR/AND explanation in more prose forma but does not add much parameter-level detail beyond the schema; a 3 is the safe baseline.

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 opening line says what the tool does: selects a slice of the signal feed by facet tags, and explicitly clarifies that matching is on structured metadata rather than words in text. It also names the sibling tool search_signals and distinguishes itself from it, so the agent can disambiguate even before reading the schemas.

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 explicitly describes the use case: call this when you can name a slice, and call search_signals when you have a subject word but no category to name. It gives concrete examples of shareable slices — severity, provider, language — and also excludes what a single locale filter can't do, which is duid to guidance.

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

All pronto-stream toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.7/5.0
Disambiguation5/5

Each tool targets a distinct operation: the two facet-listing tools are explicitly differentiated as quick manifest vs exhaustive listing, and search_signals vs scope_signals is cleanly split between lexical search and facet filtering. The billing/payment tools also form a clear lifecycle with no overlapping responsibilities.

Naming Consistency5/5

All tools follow a consistent verb_noun snake_case pattern: get_* and list_* for reads, and action verbs like register_agent, open_payment, settle_payment, scope_signals, search_signals for operations. No mixed casing or inconsistent verb styles.

Tool Count5/5

15 tools is at the upper edge of the well-scoped range but each tool earns its place: five cover data retrieval, four cover discovery/metadata, and five cover identity/billing. No redundant or filler tools.

Completeness5/5

The surface covers the full workflow for the stated domain: discover vocabulary, search/scope the live wire, retrieve individual signals and related signals, compute fused products, register an identity, and purchase/activate a plan. The only apparent omissions, such as cancellation, are outside the described prepaid self-service flow.

Resources