Skip to main content
Glama
tenatarika

vex

by tenatarika
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

find_similar

Search code by natural-language concept when no identifier is known; matches terms like 'payment processing' to relevant symbols via a semantic vector index.

Instructions

Semantic-only search by natural-language description (e.g. 'payment processing' → ChargeUseCase, BillingService). Uses the HNSW vector index built by vex index --semantic (~7-15ms). Prefer over search when you do not know any concrete identifier and want concept-level matching; prefer search when you have a partial name (search fuses semantic + lexical channels for better recall on identifier-shaped queries).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesNatural-language description of the concept (not an identifier; use find_symbol for those).
excludeNoBlacklist results by path glob; wins over include (repeatable)
includeNoWhitelist results by path glob, gitignore syntax (repeatable)
auto_updateNoAuto-update the index if stale, or bootstrap it if missing, before running (default: true)
async_updateNoWith auto_update, refresh a stale index in the background instead of waiting for it: results come from the index already on disk and _meta.vex.dev/stale says so (default: false)
project_rootNoAbsolute path to the project root (defaults to the MCP working directory)
exclude_testsNoDrop test files from the results (tests/ dirs, *_test.*, test_*.py, *.spec.ts, __tests__/, tests.rs, ...; same set as tests_for). Composes with include/exclude. Path-based only: Rust unit tests inside a `#[cfg(test)] mod tests` block of a non-test file are not excluded.
no_stale_checkNoSkip the staleness check that runs before each call; assumes the index is fresh. Redundant when `auto_update` is true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.27.3

TDQS

A4.4/5.0
Behavior4/5

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

No annotations are provided, so the description carries the burden; it discloses the underlying HNSW vector index, the ~7-15ms latency, and that the index is built by `vex index --semantic`. It does not describe return shape or result ranking, and staleness/update behavior is left largely to the schema.

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 sentences, front-loaded with the core purpose, then mechanism, then routing guidance. Dense but every sentence earns its place with no redundancy.

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

Completeness4/5

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

For an 8-parameter tool with no annotations and no output schema, the description covers purpose, routing, and index/latency behavior well. It omits return-value expectations and ranking behavior, but the routing and index context make it largely callable as-is.

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 all eight parameters are already documented, including the 'not an identifier' caveat on `query`. The description adds no parameter-level detail beyond what the schema provides, so the baseline 3 applies.

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?

States a specific verb and resource ('Semantic-only search by natural-language description') with a concrete example mapping. It explicitly distinguishes itself from `search` and `find_symbol`, so an agent can identify the tool without opening any schema.

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

Usage Guidelines5/5

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

Gives an explicit decision rule: prefer this over search when no concrete identifier is known, prefer search when a partial name exists, and use find_symbol for identifiers. Both the when and the when-not with named alternatives are present.

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