Skip to main content
Glama

Memory Recall

vault_memory_recall
Read-onlyIdempotent

Recall dated memory entries about a topic from all memory files, using hybrid keyword and semantic search to reveal the evolution of your preferences and opinions.

Instructions

Recall memory entries about a topic — entry-granular hybrid (keyword + semantic) retrieval across ALL About Me/ files and ALL time. Returns every relevant dated entry sorted oldest-first, so the full evolution of a preference, opinion, or fact is visible — semantic matching finds early entries even when their phrasing differs from the query. Tuned for recall over precision: expect some marginal entries and judge relevance yourself when synthesizing an answer. Content-word queries ("testing philosophy", "sustainable pacing") rank best; a meta-framed query ("opinions on testing") whose relevance cut would come back empty degrades to relaxed any-term keyword matching instead of returning nothing.

Example: vault_memory_recall({ query: "working hours and pacing" }) Example: vault_memory_recall({ query: "opinions on testing", file: "Opinions" })

When to use: Answering "what does my memory say about X?" or "how has my view on Y evolved?" — topic-based recall across memory files. Prefer vault_get_memory to read a known file or section verbatim; prefer vault_search for notes outside the memory layer.

Errors:

  • No matching entries returns { entries: [], total: 0 }, not an error

  • An unknown file returns empty results — call vault_list_memory_files to discover valid names

Returns: JSON { entries, total, truncated, search_mode, reranked }. Each entry is { file, section, date, text } — text is the raw entry markdown (wikilinks intact, continuation lines included); file and section feed directly into vault_get_memory or vault_delete_memory. entries ascend by date (oldest first). total counts all matched entries; truncated=true means max_results dropped the least-relevant matches — never a date range — so raise max_results or narrow the query for the complete set. search_mode is "hybrid" when vector matching contributed, "fts" when the entries came from keyword matching alone — including the any-term fallback that rescues a would-be-empty result; reranked is true when the cross-encoder relevance cut was applied.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fileNoOptional: restrict to one memory file, name without .md (e.g. "Opinions"). Omit for cross-file recall — the default and usual choice.
queryYesTopic to recall — natural language works best (semantic matching bridges phrasing drift across months); content words about the topic rank better than meta framing ("testing philosophy" over "opinions on testing")
max_resultsNoCap on returned entries (default 50). When more match, the least-relevant are dropped and truncated=true — never a date range.
Behavior5/5

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

Annotations already indicate readOnlyHint=true, destructiveHint=false, and idempotentHint=true. The description adds behavioral details beyond annotations: that the tool is tuned for recall over precision (expect marginal entries), that search_mode can be 'hybrid' or 'fts' with an any-term fallback to avoid empty results, that reranked indicates a relevance cut, and that truncated=true means least-relevant matches dropped (not a date range). No contradiction.

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?

The description is multi-paragraph but each sentence adds necessary information. It front-loads the core purpose and usage, then details behavior, errors, and return format. While not terse, it avoids redundancy and every sentence appears justified for a tool with this complexity.

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?

Despite lacking an output schema, the description fully explains the return value: JSON with entries, total, truncated, search_mode, reranked. Each entry's fields (file, section, date, text) are described, including text containing raw markdown. Edge cases (empty results returning {entries:[], total:0}, unknown file returning empty) are covered. This is complete for a read-only, idempotent tool.

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

Parameters5/5

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

Schema coverage is 100% with descriptions for all 3 parameters. The description adds significant value: for 'query' it explains natural language works best and contrasts content words vs meta framing with examples; for 'file' it clarifies omission means cross-file; for 'max_results' it explains truncation behavior. This goes well beyond the schema alone.

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 the verb 'recall' and the resource 'memory entries'. It specifies entry-granular hybrid retrieval across all About Me/ files and all time, and distinguishes from sibling tools like vault_get_memory (for known files/sections) and vault_search (for notes outside the memory layer).

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?

Explicit guidance is given: 'Answering "what does my memory say about X?" or "how has my view on Y evolved?"' as when to use, and 'prefer vault_get_memory to read a known file or section verbatim; prefer vault_search for notes outside the memory layer' as when-not and alternatives. Error behavior for empty results and unknown file is also documented.

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/aliasunder/vault-cortex'

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