Skip to main content
Glama
Sign In
grepnotes

grepnotes

by LuthfiMirza
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

search_notes

Find relevant passages in indexed notes using BM25 keyword ranking, returning file paths and line numbers so you can read only matched sections.

Instructions

Search the indexed notes and return the most relevant passages, ranked by BM25. Use this instead of reading whole files when you only need the parts of a knowledge base that match a question.

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": "search_notes"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum passages to return (default 5).
queryYesNatural language or keyword query.
path_prefixNoOptional. Restrict results to paths starting with this prefix.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior3/5

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

No annotations exist here, so the description carries the full behavior burden. It usefully discloses that results are BM25-ranked passages rather than whole documents and that the corpus is an index, but it is silent on behavior when nothing matches, whether the index can be stale, and whether results are truncated by the limit without an indication.

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?

Two sentences, no filler, with the core action and ranking stated first and the substitution guidance second. Every clause earns its place.

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?

All three parameters are self-documented and the tool is simple, but with no output schema the description must sketch the return shape, and it only says 'passages ranked by BM25' without indicating whether each passage carries its source path or offset. The mention of an index also leaves freshness assumptions unaddressed.

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%: query, limit (default 5, max 25), and path_prefix are all documented in the schema. The description adds no parameter-level detail (for example how BM25 treats operator syntax or how path_prefix interacts with the index), 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 (search) and resource (the indexed notes) plus the ranking mechanism (BM25) and the return granularity (most relevant passages). That is clearly distinct from the read_note and list_notes siblings, so an agent can route on the description alone.

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?

"Use this instead of reading whole files when you only need the parts of a knowledge base that match a question" gives an explicit selection condition and the behavior to avoid. It does not name read_note directly nor state when not to search (e.g. when the exact document is already known), so it falls just short of full coverage.

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