PseudoLife-MCP

Official

Overview Schema Source Related Servers Discussions Admin

memory_recall

Read-only

Answer relational questions by walking the knowledge graph across linked entities, chaining hops that single-shot searches cannot. Read-only, with confidence and truncation signals.

Instructions

Multi-hop retrieval over the knowledge graph, for RELATIONAL questions whose answer is reached by following links — "what does X ultimately run on?", "how does A reach C?" — which single-shot memory_search can't chain. Read-only. low_confidence: true means no seed entity matched — fall back to memory_search.

Returns: {seeds, entities, edges, paths, texts, iterations}. entities/edges/texts are capped (currently 10/15/6) with a per-hop reservation, so a hub seed's own 1-hop ring can't crowd out the deeper hops the walk exists to reach; edges prefers links between surviving entities; each entity's facts is capped (currently 5). A fact carrying re_verify stands on a memory that has since been corrected — the value still stands, but check it before acting. A seed entity's constraint facts come first, marked pinned. truncated: true (with searches_issued) means a search ceiling or time budget stopped the walk early: some re-queries, and possibly deeper hops, were skipped, so supporting texts and deeper entities may be missing — narrow the question or lower hops. Details: docs/guide/retrieval.md.

Input Schema

TableJSON Schema

Name	Required	Description
`hops`	No	Max graph hops. Clamped to 1..5.
`query`	Yes	Natural-language relational question; its top hits seed the graph walk.
`top_k`	No	Bounds only the SEED search (the initial hits that name the walk's start entities), not the result, which is capped separately; up to 3 ``texts`` slots go to seed hits.
`verbose`	No	Full fact/edge provenance and untruncated texts. Default facts are ``{attribute, value}``, edges ``{src, relation, dst}``, texts truncated to a preview.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv0.15.0Sep 3, 2026

addedInput schema / properties / hops / description

Added value: +"Max graph hops. Clamped to 1..5."

addedInput schema / properties / query / description

Added value: +"Natural-language relational question; its top hits seed the graph walk."

addedInput schema / properties / top_k / description

Added value: +"Bounds only the SEED search (the initial hits that name the walk's start entities), not the result, which is capped separately; up to 3 ``texts`` slots go to seed hits."

addedInput schema / properties / verbose / description

Added value: +"Full fact/edge provenance and untruncated texts. Default facts are ``{attribute, value}``, edges ``{src, relation, dst}``, texts truncated to a preview."

First observedv0.11.0Jul 31, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations cover only the safety profile (readOnlyHint true, destructiveHint false); the description goes well beyond by disclosing capping behavior (10/15/6 with per-hop reservation), fact cap of 5, the meaning of re_verify on corrected memories, pinned constraint facts, and what truncated/searches_issued implies about missing data. This is unusually rich behavioral context.

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?

Purpose is front-loaded in the first sentence and every later sentence carries operational detail (caps, re_verify, truncated). It is dense rather than bloated, though 'Read-only' duplicates the readOnlyHint annotation and the return-field listing slightly overlaps the output schema.

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 having an output schema, the description supplies the interpretive layer the schema cannot: what capping, re_verify, pinned facts, and truncated mean for the agent's next action. Combined with the doc pointer, nothing an agent needs to call this correctly is missing.

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%, so the baseline is 3 and the schema already documents hops, top_k, and verbose. The description still adds meaning by tying hops to the truncated failure mode ('lower hops') and explaining why results are capped independently of top_k, which the schema does not spell out.

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 (multi-hop retrieval) and resource (knowledge graph) plus the exact class of question it serves (relational, link-following). It explicitly distinguishes itself from memory_search, which 'can't chain', so an agent can route without opening either schema.

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?

Names the alternative (memory_search) and the condition that selects it, gives a fallback rule when low_confidence is true, and tells the agent to narrow the question or lower hops when truncated. When-to-use, when-not, and recovery paths are all explicit.

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