Algolia Productivity

Search Algolia Knowledge

algolia_knowledge_search

Read-only

Answer a general question about Algolia from Algolia's official documentation and support articles. Returns passages, each with its source URL. Use this for questions about how Algolia works, what a parameter or concept means, plan and billing questions, error messages, and troubleshooting. This content is keyword-matched, not semantic: pass distilled search terms, not the user's sentence, and pass several variants so a vocabulary mismatch in one does not lose the answer.

Input Schema

TableJSON Schema

Name	Required	Description
`question`	Yes	The user's question verbatim, one sentence, no greetings or backstory. Searched as written: these pages are titled as questions, so the user's own wording often matches a title that keywords miss.
`maxResults`	No	Maximum passages to return (default 3, max 5).
`userIntent`	No	How the LLM interpreted the user's intention and decided to use available tools to achieve the result. Describe the user's goal and the reasoning behind choosing this tool (e.g., 'User wants affordable Nike shoes under $100 - using search with price/brand filters to narrow results'). This helps understand the LLM's decision-making process for tool selection.
`searchTerms`	Yes	The same question translated for a keyword engine: up to 5 short phrases built from words the page itself would use — the feature or parameter name, the symptom, the likely title. The index is lexical, not semantic, so a word the page never uses cannot match. Results are ranked by agreement across phrases, so vary them rather than repeating. e.g. ["virtual replica usage", "replica record count", "replica billing"]
`originalQuery`	No	The original, unmodified user prompt that was sent to the LLM. This helps track how the LLM interpreted the user's request and decided to use this tool. Include the complete original message for context and debugging purposes.

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 5, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Annotations cover the safety profile (read-only, non-destructive, closed-world), and the description adds genuinely non-obvious behavior: retrieval is lexical keyword matching, not semantic, results are ranked by agreement across phrases, and each returned passage carries its source URL. That is exactly the mechanism an agent must understand to call this correctly.

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 purpose, then return shape, then use-case enumeration, then query-construction guidance. Dense and waste-free, though the middle use-case list is somewhat enumerative rather than strictly necessary.

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?

With no output schema, the description supplies the return format (passages plus source URLs) itself, covers when to use it, and explains input construction. Combined with fully documented parameters and safety annotations, nothing an agent needs to invoke it correctly is missing.

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 baseline is 3; the description goes further by explaining why distilled variants of searchTerms are needed ('a vocabulary mismatch in one does not lose the answer') and why the question is passed verbatim (pages are titled as questions). It adds rationale and usage nuance beyond the schema text.

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?

States a specific verb and resource: answer general Algolia questions from official documentation and support articles. The resource scope (docs/support content) clearly separates it from the sibling tools that manipulate the tool catalog, though no sibling is named explicitly.

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?

Enumerates concrete when-to-use contexts: how Algolia works, parameter/concept definitions, plan and billing questions, error messages, troubleshooting. It also specifies when keyword search beats semantic search, but states no explicit exclusion or named alternative tool.

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

All Algolia Productivity 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.

Resources

Need Help?