Skip to main content
Glama

perseus_memory

Read-only

Search local project memory for past decisions and architecture notes using FTS5 full-text search. Retrieve relevant results for in-workspace recall without network dependency.

Instructions

Search LOCAL project memory (FTS5, zero-network) for past decisions and architecture notes. Use for in-workspace recall. For cross-session persistent facts, use perseus_mneme instead. Read-only; returns results array with mode and count.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kNoNumber of results to return (default: 5)
modeNoQuery mode: search, narrative, or federation
typeNoMemory type filter
aliasNoWorkspace alias for federation targeting
focusNoTime focus: recent, today, week, or all
forceNoValue for force parameter
limitNoValue for limit parameter
queryNoSearch query string for BM25 / hybrid recall
scopeNoMemory scope filter: working, core, or all
renderNoIf 'true', render matched memories as markdown
projectNoValue for project parameter
workspaceNoTarget workspace path for scoped queries
federationNoEnable cross-workspace federation
max_tokensNoValue for max_tokens parameter
include_federationNoInclude federation results in output

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoQuery mode used
countNoNumber of results returned
resultsNo
Behavior4/5

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

Annotations already declare readOnlyHint=true, and the description reinforces 'Read-only' and adds context about the return format ('returns results array with mode and count'). This goes beyond annotations without contradicting them.

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 concise with two sentences covering purpose, usage guidelines, and behavioral notes. Every word adds value with no redundancy.

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?

Despite having 15 parameters (all optional) and an output schema, the description adequately covers the core functionality, usage context, and behavioral aspects. It could provide more detail on common parameter combinations but remains sufficiently complete for an AI agent.

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% with all 15 parameters described in the input schema. The description adds no additional semantics beyond what the schema provides, so baseline score of 3 is appropriate.

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 tool searches LOCAL project memory with specific technical details (FTS5, zero-network) for past decisions and architecture notes. It distinguishes itself by emphasizing 'in-workspace recall' and contrasts with sibling perseus_mneme for cross-session facts.

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?

The description explicitly advises using this tool for in-workspace recall and directs to perseus_mneme for cross-session persistent facts, providing clear when-to-use and when-not-to-use guidance with a named alternative.

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/Perseus-Computing-LLC/perseus'

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