Brainiall Memory

Recall Memories

recall

Read-onlyIdempotent

Search persistent memory by semantic meaning to retrieve past facts, context, or preferences.

Use when answering queries that benefit from prior user context, past decisions, or stored preferences. Performs vector search (semantic similarity) rather than simple keyword match.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Maximum number of memory items to return (default: 5, ceiling: 50).
`query`	Yes	Search query describing the fact, context, or topic to find by semantic similarity.
`namespace`	Yes	Storage namespace to search (e.g., 'user_123_pref', 'agent_project_alpha').

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering the safety profile. The description adds the key behavioral trait of performing vector-based semantic search rather than keyword match, which is not captured in annotations. This is valuable context but not exhaustive; yet with annotations covering other aspects, a high score is warranted.

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 extremely efficient: two sentences that state purpose, usage, and the semantic search mechanism. No wasted words, and essential information is front-loaded. Exemplary conciseness.

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?

With an output schema present, return values need not be explained. The description covers purpose, usage, and the core behavioral distinction. Combined with annotations (read-only, idempotent) and full parameter docs, the tool is adequately specified. Slight lack of mention of the 'namespace' parameter's role in isolation is minor.

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 coverage is 100%, so each parameter is already described. The description adds the semantic similarity emphasis for 'query', which slightly reinforces its purpose but does not introduce new meaning. Baseline of 3 is appropriate given high schema coverage.

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 persistent memory by semantic meaning to retrieve past facts, context, or preferences. It explicitly contrasts with simple keyword match, which helps distinguish it from other retrieval approaches. Even without referencing siblings, the purpose is unambiguous.

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?

It provides clear guidance on when to use the tool: when queries benefit from prior user context, past decisions, or stored preferences. It does not explicitly name alternatives like 'recent_memories' or 'remember', but the semantic distinction is implied. A brief mention of when not to use it would have earned a 5.

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

All Brainiall Memory tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose: remember stores, recall searches semantically, recent_memories lists by recency, and check_memory_service monitors health. There is no meaningful overlap between the retrieval tools because one is query-driven and the other is time-driven.

Naming Consistency2/5

Naming is inconsistent: remember and recall are bare verbs, recent_memories is a noun phrase, and check_memory_service uses a verb_noun pattern. A more consistent set would use e.g. remember, recall, list_recent_memories, check_service_health.

Tool Count5/5

Four tools is well-scoped for a persistent memory service. Each tool covers a distinct, necessary operation without redundancy or bloat.

Completeness3/5

The core create/read and health-check operations are present, but there is no update or delete tool for managing stored memories. This creates a notable lifecycle gap, especially for correcting or removing outdated facts.

Resources

Need Help?