Skip to main content
Glama

semantic_search

Idempotent

Search concepts by meaning using vector embeddings to retrieve ranked matches, with optional scope, entity-type, and frequency filters for targeted results.

Instructions

Search concepts semantically using vector embeddings.

Returns {cached, count, results}: results are the matching concepts with scores, ordered by similarity; cached=true marks a TTL-cache hit. Pass scope to constrain retrieval to a named scope (see scope_list); a scoped response names the scope that governed it.

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
limitNo
queryYes
scopeNo
frequencyNo
entity_typeNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior4/5

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

Adds real behavior beyond the annotations: results are ordered by similarity, each carries a score, and cached=true marks a TTL-cache hit — which usefully explains why a search tool is annotated readOnlyHint=false. It stops short of describing pagination, whether caching affects freshness, or how empty results are represented.

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 the core action, then return shape, then the scope caveat — a sensible order with no filler sentences. The return-shape sentence partially duplicates the existing output schema, which is the only real waste.

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

Completeness2/5

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

For a tool with 5 undocumented parameters and three semantically adjacent siblings, the definition leaves too much unresolved: no query semantics, no meaning for frequency or entity_type, and no guidance on choosing among the search variants. The presence of an output schema excuses it from deeper return documentation, but not from the parameter gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for 5 parameters, so the description must carry the burden and does not. Only ``scope`` is explained; ``query``, ``limit``, ``frequency``, and ``entity_type`` get no meaning, format, or accepted-values guidance anywhere in the definition.

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: semantic vector search over 'concepts', which distinguishes it somewhat from entity-oriented siblings by naming the target object. However, it never says how it differs from semantic_search_unified or ai_search, so an agent comparing those siblings gets no routing signal from the description itself.

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 only usage guidance is the note to pass ``scope`` when retrieval should be constrained, with a pointer to scope_list. There is no statement of when to prefer this over the other semantic/graph search tools, and no exclusions or prerequisites, leaving selection implied rather than directed.

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