Synorb: News & Context for AI Agents

synorb-stream-search

Read-onlyIdempotent

Search accessible Stream/source inventory with typo and synonym handling. 17-digit Synorb ID values: pass them as JSON strings, never a number. USE THIS WHEN: the user asks what streams/sources/podcasts/publishers are available. DO NOT USE THIS WHEN: the user needs actual Manifest content or already named exact content filters.

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": "synorb-stream-search"
  }
}

Input Schema

Name	Required	Description	Default
`isin`	No	Exact equity ISIN(s).
`page`	No	Zero-based page index.
`query`	No	Inventory/source search text.
`ticker`	No	Exact public-company ticker(s).
`segment`	No	Segment id, e.g. 'ai_companies:coding'; a parent covers its sub-segments.
`surface`	No	Canonical surface id, e.g. 'public_companies'. Unknown ids list valid ones.
`page_size`	No	Inventory results per page; capped.
`verbosity`	No	minimal, standard, or verbose.	minimal
`home_domain`	No	Single canonical home domain.
`company_kind`	No	Optional facet: public or private.
`home_domains`	No	Canonical domains or ['all'].
`media_format`	No	Content surface, e.g. text/audio/data.
`cross_domains`	No	Up to 3 secondary domains.
`segment_match`	No	any or primary.
`query_relation`	No	auto is broad. exact_names resolves declared Stream names. compound_topic needs all concepts in one Stream's text. topic_set is a broad union. Catalog evidence only.	auto
`include_details`	No	Include source-channel summaries.
`inventory_scope`	No	Inventory scope label.	live_public_active_mcp
`proof_stream_id`	No	Internal diagnostic Stream ID string. Does not filter or rank.
`cross_domain_logic`	No	'or' for any, 'and' for all.	or
`organization_subtype`	No	Exact organization tag subtype, e.g. public_company.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 3, 2026

addedInput schema / properties / segment

Added value: +{
+  "default": "",
+  "description": "Segment id, e.g. 'ai_companies:coding'; a parent covers its sub-segments.",
+  "title": "Segment",
+  "type": "string"
+}

addedInput schema / properties / segment_match

Added value: +{
+  "default": "",
+  "description": "any or primary.",
+  "title": "Segment Match",
+  "type": "string"
+}

First observedOct 23, 2026

TDQS

A3.7/5.0

Behavior3/5

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

With readOnlyHint and idempotentHint declared, the description need not re-litigate safety, and it correctly does not. It discloses two genuinely beyond-schema behaviors: fuzzy typo/synonym matching, and that unknown surface ids will enumerate valid ones. It omits the most consequential behavioral facts for a 20-parameter search — how paging terminates, whether page_size is truly capped, and what 'Catalog evidence only' means for result trustworthiness.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short blocks — purpose, encoding warning, when/when-not — with the critical ID constraint placed before the routing advice so it is read before the agent builds arguments. No filler sentences and no restatement of the tool title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-shape explanation is rightly omitted, and the when/when-not framing covers the main routing need. But for a 20-parameter tool with 12 sibling tools, the description says nothing about which parameter families are mutually exclusive or how the facet parameters (ticker, isin, surface, segment, home_domain) combine, leaving a large surface for misuse.

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?

Annotations already carry the full safety profile (readOnly, idempotent, openWorld, non-destructive), so the description's job is to add operational context. It does add one valuable detail — the 17-digit Synorb ID must be passed as a JSON string, never a number — which prevents a real precision-loss failure. Beyond that it offers no guidance on the more consequential knobs (verbosity levels, inventory_scope labels, segment_match behavior) that the schema only labels briefly.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence names a specific verb and resource ('Search accessible Stream/source inventory') plus a distinguishing capability ('typo and synonym handling'). It stops short of naming the sibling it shadows (synorb-catalog / synorb-manifests), so the agent must infer separation from the 'DO NOT USE' line rather than from an explicit contrast.

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?

Explicit USE THIS WHEN / DO NOT USE THIS WHEN blocks give both the positive trigger (user asks what streams/sources/podcasts/publishers are available) and two exclusions (needing Manifest content, already having exact named filters). The exclusions point at a behavior rather than naming the alternative tool, so routing is clear but not definitive.

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

All Synorb: News & Context for AI Agents tools Inspect

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.