Skip to main content
Glama
semlayer MCP server

semlayer MCP server

semantic_search

Read-onlyIdempotent

Search tables, columns, and metrics by keyword to identify the right business data and start warehouse queries with correct context.

Instructions

Search tables, columns, and metrics by keywords. The starting point.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "semantic_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYesKeywords or a short phrase, such as 'refunds by region'. Matched on stemmed words, with abbreviations expanded, against the names and descriptions of tables, columns and metrics; it is not an embedding search. The best matches come back ranked, canonical tables above staging and deprecated ones.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.1
    • addedInput schema / properties / query / description
      Added value: +"Keywords or a short phrase, such as 'refunds by region'. Matched on stemmed words, with abbreviations expanded, against the names and descriptions of tables, columns and metrics; it is not an embedding search. The best matches come back ranked, canonical tables above staging and deprecated ones."
  2. First observedv0.1.0

TDQS

B3.2/5.0
Behavior2/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and a closed-world scope, so the core safety profile is covered. Beyond that, the description adds only the vague phrase 'the starting point' and says nothing about result ranking, result limits, or how staging/deprecated objects appear. The substantive behavioral detail about stemmed matching and canonical-table ranking lives in the parameter schema, not the tool description.

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?

Two short sentences with the primary action front-loaded and no boilerplate. The second sentence is a fragment ('The starting point') that is terse to the point of being cryptic, which keeps it from a 5.

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?

With an output schema present, return values need not be explained, and the single parameter is fully documented in the schema. However, for a discovery entry-point tool the description is thin: it does not say what a caller should do with the results or when to switch to get_tables/table_detail, leaving the workflow incomplete.

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?

There is a single required parameter with 100% schema description coverage, and that schema text is rich, explaining stemming, abbreviation expansion, non-embedding matching, and ranking of canonical over staging and deprecated objects. The tool description contributes no additional parameter meaning, so the baseline of 3 applies.

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 description gives a concrete verb and resource set: search tables, columns, and metrics by keywords. This is distinguishable from list-style siblings like get_tables or get_metrics, and 'the starting point' signals an entry/discovery role. It stops short of stating explicitly how it differs from siblings, so it is clear but not fully differentiated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'The starting point' implies this should be used first when looking for data assets, which is weak but real usage guidance. There is no explicit when-not, no named alternative for browsing versus searching, and no note about what to do after obtaining results.

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