Skip to main content
Glama

vault_search

Read-onlyIdempotent

Search a knowledge vault using full-text queries, ranked relevance, or recent changes. Apply filters by type, status, tag, project, or scope.

Instructions

Search the vault: full-text, ranked, or recent changes.

Default mode: flat full-text search across all vault files. Ranked mode (ranked=True): results scored by relevance. Recent mode (since_days>0): files changed in the last N days. rank_by mode (rank_by != 'bm25'): lessons-only, ranked by usage.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryNoText to search for (case-insensitive).
max_linesNoMaximum output lines. Default 500.
type_filterNoOnly files whose frontmatter type matches.
status_filterNoOnly files whose frontmatter status matches.
tag_filterNoOnly files that have this frontmatter tag.
use_regexNoTreat query as regex. Default False. (Use `use_regex`, not `regex` — `regex` is accepted as an alias.)
rankedNoScore results by relevance. Default False.
max_resultsNoMax result files. Default 10. Caps the file count in all modes (flat, ranked, recent); in flat/recent the cap is by path order (alphabetical) — use ranked=True for relevance order.
since_daysNoShow recent changes (0 = disabled). Default 0.
projectNoFilter to this project (recent mode only).
scopeNoRestrict search to a scope (e.g. 'work', 'projects'). Empty = all.
rank_byNoLesson ranking ('bm25' default keeps current behaviour; 'reinforcements', 'confidence', 'hybrid' filter to 90-lessons.md only and rank by usage signal).bm25
regexNoAlias of `use_regex` (#151). Prefer `use_regex`. To narrow by location use `scope` / `project`, not `path_filter` / `path_prefix`.
limitNoAlias of `max_results` (#202). Prefer `max_results`. When both are given the tighter (smaller) cap wins; 0 = unset.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior4/5

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

Annotations already declare readOnlyHint and idempotentHint. The description adds behavioral details about modes, aliases (regex, limit), and cap interactions without contradicting annotations.

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?

The description is concise (4 lines) yet comprehensive, using clear bullet-like phrasing to convey modes and key behaviors without extraneous text.

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

Completeness5/5

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

The description covers all modes, parameter interactions, and aliases. With an output schema present, return values need not be described. Sufficient for a complex search tool.

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

Parameters4/5

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

Schema coverage is 100%. The description adds value by explaining aliases (regex vs use_regex, limit vs max_results) and mode-specific parameter effects.

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?

The description clearly states it searches vault files with multiple modes (full-text, ranked, recent), distinguishing it from sibling tools like vault_query or vault_list.

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?

The description explains when to use each mode (default, ranked, recent, rank_by) but does not explicitly exclude alternatives or state when not to use this tool.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/mlorentedev/hive'

If you have feedback or need assistance with the MCP directory API, please join our Discord server