savvly

Search Savvly Q&A Content Library

search_savvly_content

Read-onlyIdempotent

Search the Savvly Q&A Content Library — audience-tagged questions and answers compiled from Savvly's marketing collateral plus the factual FAQ, organized by stakeholder (employee, advisor, broker, employer, universal, general) and section (kebab-case slugs, e.g. 'tax-legacy', 'retention-talent-strategy', 'implementation'). Use this when the user asks about Savvly's positioning, value props, audience-specific talking points, or Q&A-style messaging. Each entry carries the verbatim answer plus any disclaimer footnotes attached to it in the source. These facts come from Savvly's own current records; the response includes primary sources (e.g. SEC filings) for reference.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Cap on matched entries returned. Default 20, max 50.
`query`	No	Free-text search over questions, answers, and footnotes (case-insensitive). Multi-word queries match entries containing ANY of the words, ranked by relevance.
`section`	No	Substring match against section slugs (e.g. 'tax', 'retention', 'eligibility'). Case-insensitive.
`audience`	No	Restrict to one stakeholder audience. Use EXACTLY one of: 'employee', 'advisor', 'broker', 'employer', 'universal', or 'general' ('general' is the factual FAQ). Omit to search across all audiences.

Output Schema

TableJSON Schema

Name	Required	Description
`entries`	Yes	Matched Q&A entries.
`matched`	Yes	Count of entries matching the supplied filters.
`filter_applied`	Yes	Echo of the filters that produced this result set.
`total_in_library`	Yes	Total Q&A entry count in the library across all audiences.
`available_sections`	Yes	Section slugs available within the (optionally) selected audience.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedAug 23, 2026

removedInput schema / properties / session_id

Removed value: -{
-  "description": "REQUIRED on every call after your first. This MCP server associates all of your tool calls for a given task using session_id; a call that arrives without it cannot be associated with your earlier work and is treated as the start of an unrelated task, disconnected from the original goal. Omit it on your first call only — the server will issue one in the _mcp_instructions field of the result (or a trailing [MCP INSTRUCTIONS] text block) — then echo that exact value on every later call. Never invent a value, and do not issue parallel tool calls until the server has issued your session_id. One session_id covers the whole goal from start to finish: when you spawn subagents you MUST give them this same session_id, or their work is severed from yours. Without session_id, this server does not function as intended.",
-  "type": "string"
-}

removedOutput schema / properties / _mcp_instructions

Removed value: -{
-  "description": "Your handles for this task, confirmed by this MCP server on every response, and the instructions for echoing them on later calls. Read and follow.",
-  "properties": {
-    "instructions": {
-      "type": "string"
-    },
-    "session_id": {
-      "description": "Echo this exact value as the session_id argument on every subsequent tool call.",
-      "type": "string"
-    }
-  },
-  "type": "object"
-}

Changed17 schema fields changedAug 23, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

removedInput schema / additionalProperties
```
Removed value: -false
```

addedInput schema / properties / session_id

Added value: +{
+  "description": "REQUIRED on every call after your first. This MCP server associates all of your tool calls for a given task using session_id; a call that arrives without it cannot be associated with your earlier work and is treated as the start of an unrelated task, disconnected from the original goal. Omit it on your first call only — the server will issue one in the _mcp_instructions field of the result (or a trailing [MCP INSTRUCTIONS] text block) — then echo that exact value on every later call. Never invent a value, and do not issue parallel tool calls until the server has issued your session_id. One session_id covers the whole goal from start to finish: when you spawn subagents you MUST give them this same session_id, or their work is severed from yours. Without session_id, this server does not function as intended.",
+  "type": "string"
+}

changedOutput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

addedOutput schema / properties / _mcp_instructions

Added value: +{
+  "description": "Your handles for this task, confirmed by this MCP server on every response, and the instructions for echoing them on later calls. Read and follow.",
+  "properties": {
+    "instructions": {
+      "type": "string"
+    },
+    "session_id": {
+      "description": "Echo this exact value as the session_id argument on every subsequent tool call.",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

addedOutput schema / properties / filter_applied / properties / audience / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

removedOutput schema / properties / filter_applied / properties / audience / type
```
Removed value: -[
-  "string",
-  "null"
-]
```
addedOutput schema / properties / filter_applied / properties / limit / maximum
```
Added value: +9007199254740991
```
addedOutput schema / properties / filter_applied / properties / limit / minimum
```
Added value: +-9007199254740991
```

addedOutput schema / properties / filter_applied / properties / query / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

removedOutput schema / properties / filter_applied / properties / query / type
```
Removed value: -[
-  "string",
-  "null"
-]
```

addedOutput schema / properties / filter_applied / properties / section / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

removedOutput schema / properties / filter_applied / properties / section / type
```
Removed value: -[
-  "string",
-  "null"
-]
```
addedOutput schema / properties / matched / maximum
```
Added value: +9007199254740991
```
addedOutput schema / properties / matched / minimum
```
Added value: +-9007199254740991
```
addedOutput schema / properties / total_in_library / maximum
```
Added value: +9007199254740991
```
addedOutput schema / properties / total_in_library / minimum
```
Added value: +-9007199254740991
```

Changed1 schema field changedJul 20, 2026

changedInput schema / properties / audience / description

Previous value: -"Restrict to one stakeholder audience ('general' is the factual FAQ). Omit to search across all audiences."New value: +"Restrict to one stakeholder audience. Use EXACTLY one of: 'employee', 'advisor', 'broker', 'employer', 'universal', or 'general' ('general' is the factual FAQ). Omit to search across all audiences."

Changed1 schema field changedJul 14, 2026

changedInput schema / properties / audience / description

Previous value: -"Restrict to one stakeholder audience ('general' is the factual FAQ). Use the exact lowercase token (the enum is case-sensitive). Omit to search across all audiences."New value: +"Restrict to one stakeholder audience ('general' is the factual FAQ). Omit to search across all audiences."

Changed1 schema field changedJul 7, 2026

changedInput schema / properties / audience / description

Previous value: -"Restrict to one stakeholder audience ('general' is the factual FAQ). Omit to search across all audiences."New value: +"Restrict to one stakeholder audience ('general' is the factual FAQ). Use the exact lowercase token (the enum is case-sensitive). Omit to search across all audiences."

Changed14 schema fields changedJun 30, 2026

changedInput schema / properties / audience / description

Previous value: -"Restrict to one stakeholder audience. Omit to search across all audiences."New value: +"Restrict to one stakeholder audience ('general' is the factual FAQ). Omit to search across all audiences."

changedInput schema / properties / audience / enum

Previous value: -[
-  "employee",
-  "advisor",
-  "broker",
-  "employer",
-  "universal"
-]New value: +[
+  "employee",
+  "advisor",
+  "broker",
+  "employer",
+  "universal",
+  "general"
+]

addedInput schema / properties / section

Added value: +{
+  "description": "Substring match against section slugs (e.g. 'tax', 'retention', 'eligibility'). Case-insensitive.",
+  "type": "string"
+}

removedInput schema / properties / subsection

Removed value: -{
-  "description": "Substring match against subsection labels (e.g. 'Tax', 'Retention', 'Eligibility'). Case-insensitive.",
-  "type": "string"
-}

addedOutput schema / properties / available_sections

Added value: +{
+  "description": "Section slugs available within the (optionally) selected audience.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

removedOutput schema / properties / available_subsections

Removed value: -{
-  "description": "Subsection labels available within the (optionally) selected audience.",
-  "items": {
-    "type": "string"
-  },
-  "type": "array"
-}

changedOutput schema / properties / entries / items / properties / audience / enum

Previous value: -[
-  "employee",
-  "advisor",
-  "broker",
-  "employer",
-  "universal"
-]New value: +[
+  "employee",
+  "advisor",
+  "broker",
+  "employer",
+  "universal",
+  "general"
+]

addedOutput schema / properties / entries / items / properties / keywords

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

removedOutput schema / properties / entries / items / properties / subsection
```
Removed value: -{
-  "type": "string"
-}
```

changedOutput schema / properties / entries / items / required

Previous value: -[
-  "id",
-  "audience",
-  "section",
-  "subsection",
-  "question",
-  "answer",
-  "footnotes"
-]New value: +[
+  "id",
+  "audience",
+  "section",
+  "question",
+  "answer",
+  "footnotes"
+]

addedOutput schema / properties / filter_applied / properties / section
```
Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}
```
removedOutput schema / properties / filter_applied / properties / subsection
```
Removed value: -{
-  "type": [
-    "string",
-    "null"
-  ]
-}
```

changedOutput schema / properties / filter_applied / required

Previous value: -[
-  "audience",
-  "subsection",
-  "query",
-  "limit"
-]New value: +[
+  "audience",
+  "section",
+  "query",
+  "limit"
+]

changedOutput schema / required

Previous value: -[
-  "total_in_library",
-  "matched",
-  "filter_applied",
-  "available_subsections",
-  "entries"
-]New value: +[
+  "total_in_library",
+  "matched",
+  "filter_applied",
+  "available_sections",
+  "entries"
+]

Changed1 schema field changedJun 20, 2026

changedInput schema / properties / query / description

Previous value: -"Free-text substring filter applied to questions, answers, and footnotes. Case-insensitive."New value: +"Free-text search over questions, answers, and footnotes (case-insensitive). Multi-word queries match entries containing ANY of the words, ranked by relevance."

First observedMay 27, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds meaningful behavioral context: entries carry 'verbatim answer plus any disclaimer footnotes,' and responses include 'primary sources (e.g. SEC filings)' for reference. This goes beyond annotations by describing data provenance and content structure. No contradiction with annotations.

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 well-structured, front-loading the core purpose and use case, then adding content details and source attribution. Each sentence contributes value: purpose, when-to-use, data characteristics, and provenance. It is somewhat lengthy but not redundant. A slightly tighter version could condense the examples, but overall it's efficient and organized.

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

Completeness5/5

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

Given the existence of an output schema (noted in context signals), the description does not need to explain return values. Annotations cover safety, and the description provides comprehensive context: what the library contains, how it's organized, when to use it, and what each entry includes (verbatim answers, footnotes, primary sources). For a read-only search tool with four optional parameters, nothing essential is missing for correct invocation.

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 description coverage is 100% (all four parameters have descriptions), baseline 3. The description adds value by specifying multi-word query behavior ('match entries containing ANY of the words, ranked by relevance') and provides concrete examples for section slugs ('tax-legacy', 'retention-talent-strategy') and clarifies audience semantics ('general' is the factual FAQ). It also notes substring matching for section. These details enhance the schema's minimal descriptions.

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 clearly states the verb (search), the resource (Savvly Q&A Content Library), and the content type (audience-tagged questions and answers). It differentiates from siblings by specifying the use case: 'positioning, value props, audience-specific talking points, or Q&A-style messaging,' which distinguishes it from get_savvly_faq (likely a static FAQ) and other tools. The organization by stakeholder and section is also included, making the purpose unambiguous.

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 explicitly says 'Use this when the user asks about Savvly's positioning...' providing clear when-to-use guidance. However, it does not explicitly mention when NOT to use it or name specific alternatives, though the sibling list and context imply get_savvly_faq might serve the full FAQ. It also clarifies the 'general' audience as the factual FAQ, giving additional contextual direction. Lacks explicit exclusions but is still strong.

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

All savvly 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.

Search Savvly Q&A Content Library

Input Schema

Output Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources