Skip to main content
Glama

Pronto

by stream.pronto.api

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. Changed1 schema field changed
    • changedInput schema / properties / limit / description
      Previous value: -"Maximum signals to return (default 200, max 1000)"New value: +"Maximum signals to return (default 25, max 200)"
  3. Changed1 schema field changed
    • changedInput schema / properties / limit / description
      Previous value: -"Maximum signals to return (default 25, max 200)"New value: +"Maximum signals to return (default 200, max 1000)"
  4. Changed1 schema field changed
    • addedInput schema / properties / relate
      Added value: +{
+  "description": "Also 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.",
+  "type": "boolean"
+}
  5. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already cover readOnly, openWorld, and idempotent, so the bar is lower. The description adds genuine behavioral context beyond those flags: the OR/AND composition semantics, the fact that the result slice is independent of the words used, and the caveat that a locale filter alone cannot answer a language question.

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 description is front-loaded: first sentence states purpose, first paragraph gives when-to-use and sibling differentiation, second paragraph adds filter semantics with a worked example. It loses slight points because the facet list and OR/AND rule are repeated nearly verbatim in the schema's filter parameter description, making the wording mildly redundant overall.

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 zero-required, parameter-light tool, this is largely complete: what it does, when to prefer it, how filter combination works, and what a successive cursor needs are all documented. The one gap is that with no output schema, the description never specifies the shape of a returned signal object; it says what the slice is but not its structure.

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 the heavy lifting is already done by the input schema (limit defaults, cursor semantics, filter pattern, relate meaning). The description adds meaningful semantics on top: walking through 'country:JP,country:CL domain:climate' as Japan-or-Chile AND climate, and warning that locale does not subsume language, which goes beyond the schema's own key list.

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 and resource — 'Select a slice of the live signal by facet tags' — and immediately clarifies that matching is by structured metadata, not text content. It explicitly differentiates itself from search_signals ('which is what separates it from search_signals'), so an agent can distinguish sibling tools without inspecting their 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 states the when-to-use condition directly: 'Use this when you can name the slice you want', with concrete examples (high-severity climate signals in Japan, one provider, one language). It also gives the exclusion rule by routing to the alternative: 'reach for search when you have a subject word and no category to name.' Selection guidance is explicit and unambiguous.

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

All Pronto 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

A4.6/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: get_signal re-reads a known row, get_latest_signals fetches by time, scope_signals filters by facets, search_signals matches words, and get_related_signals follows links. The overlapping pairs like get_facet_manifest/list_facets and get_fused_signal/list_fusion_products are explicitly differentiated in their descriptions, so an agent should not confuse them.

Naming Consistency5/5

The naming follows a consistent snake_case verb_noun pattern: get_ for direct fetches, list_ for catalog-style enumeration, register_ for identity creation, and scope_/search_ for query actions. The slight difference between get_fused_signal and list_fusion_products is meaningful and the verbs remain predictable.

Tool Count5/5

Thirteen tools is well within the sweet spot and each one covers a distinct capability: live reads, lookup by id, lexical search, facet filtering, related signals, fused products, catalogues, plans, billing, and agent registration. There is no obvious padding or excessive fragmentation.

Completeness5/5

The surface fully covers the domain: discovering the vocabulary, selecting signals, searching, fetching by id, following relationships, computing derived products, listing sources, and checking billing/plans. The only gaps would be account claiming and credential rotation, but those are explicitly deferred to external parties, so they are not tool-set gaps.

Resources