Skip to main content
Glama
MOmayr

MCP PostgreSQL Server

by MOmayr
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

resolve_mentions

Resolve mentioned entities to database matches via trigram search. Returns candidate rows, not confirmed matches.

Instructions

Trigram search. Resolve mentioned entities to database matches. Returned rows are candidates, not confirmed matches.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMax rows per query string (default 5, max 100)
tableYesTable name
whereNoSQL WHERE fragment applied with the trigram predicate (no WHERE keyword)
schemaNoSchema (default: public)
columnsNoPayload columns. Omit for all. score is added unless include_scores is false.
mentionsYesSearch strings (max 20). A single string is accepted as one element.
operatorNooperator=trgm (default) uses % and similarity(). operator=word uses %> and word_similarity().
text_columnYesText column to match. A trigram index on this column is optional.
include_scoresNoDefault true. When false, omit the score column. Ranking is unchanged.
response_formatNoEmpty for JSON. "markdown" returns one table per query string, headed Results for {text}.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.3

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full behavioral burden. It usefully warns that results are candidates rather than confirmed matches, but omits whether the operation is read-only, what happens with no trigram index, and any performance or permission considerations for a 10-parameter database tool.

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?

Three short sentences with the mechanism front-loaded and the most decision-relevant caveat placed last. Nothing is padded, though the sentences are terse enough that some explanatory value is left on the table.

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?

For a 10-parameter tool with no output schema, the description does the minimum: it hints at the matching mechanism and result semantics. It does not describe the returned row structure, scoring behavior, or multi-mention result grouping, leaving the agent to infer these from the schema alone.

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?

Schema description coverage is 100%, so the schema already documents limit, operator, include_scores, and the rest. The description's mention of trigram matching and the optional index marginally aids interpretation of operator and text_column, but adds no new parameter-level detail. Baseline 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 names a specific mechanism (trigram search) and a concrete verb+resource (resolve mentioned entities to database matches). It is distinguishable from siblings like vector_search and query, though it never states the operation is a fuzzy string match against a single text column, which would sharpen the contrast.

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

Usage Guidelines2/5

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

No guidance on when to prefer this over query, vector_search, or execute. The only contextual hint is the caveat that returned rows are candidates, which tells the agent how to interpret results but not when to reach for this tool.

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

Deploy Server

Other Tools