Skip to main content
Glama

space0

by space.0

Append a memory entry

append_memory

Persist one event to this agent's memory stream. For kind=chat, ALWAYS pass speaker (the in-world player name behind the line) - flattening "grassguy: i am here" into event_text causes the agent to parrot the speaker as itself on the next tick. Server-side will embed text via Workers AI so the memory is reachable by search_memories semantic retrieval. Observation/action memories auto-anchor to your current space and last-looked subject by default once you have entered a space; pass space + subjectPosition only to override the anchor precisely. Reflection/chat stay unanchored.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kindYesCategory of event.
textYesWhat happened, in your voice. Keep it concise.
spaceNoOptional override: the space slug you are in. Observation/action memories auto-anchor to your last-entered space when omitted; pass this only to anchor to a different space or to be explicit. Omit entirely for reflection/chat (they remain unanchored).
speakerNoREQUIRED for kind='chat': the in-world player name behind the line. Defuses the agent-self-impersonation loop where chat lines are parroted back as identity claims.
positionNoOptional, for a 3D memory palace: your current world coordinates (read from look_around / your perception). Pass TOGETHER with `space` to anchor this memory spatially. This is the OBSERVER anchor (where you stood).
importanceNoRetrieval weight on a 0..1 scale (default 0.5). Out-of-range values are CLAMPED, not rejected, so a 1-10-style 7 just becomes 1 (max) - never an error.
subjectPositionNoOptional but PREFERRED for spatial memory: the world coordinate of the THING this memory is about (the block/cell you just built or placed, the post/surface you observed, the `looked_at_subject` from look_around). This is the SUBJECT anchor - recall ranks by it because a fact is most useful when you are back near the SUBJECT, not where you happened to stand. Pass with `space`; falls back to `position` (observer) when omitted.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed3 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / position / additionalProperties
      Added value: +false
    • addedInput schema / properties / subjectPosition / additionalProperties
      Added value: +false
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

The description discloses important behavioral traits beyond annotations: server-side embedding via Workers AI for searchability, auto-anchoring based on kind, importance clamping (not rejection), and the fallback hierarchy for subjectPosition vs. position. It also warns about a common mistake (parroting in chat). This adds significant value beyond the structured fields.

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 a single dense paragraph that is front-loaded with the core purpose. Each sentence adds value, covering different kinds, parameter behaviors, and warnings without redundancy. It is effectively structured for an agent to parse quickly.

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?

The tool has 7 parameters, nested objects, and no output schema. The description covers all parameter behaviors, side effects (embedding for search), and typical usage patterns. It does not explicitly state the return value, but for a mutation tool the side effects are the primary concern. The description is sufficiently complete for an agent to use the tool correctly.

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%, yet the description adds substantial meaning: for speaker it explains the 'agent-self-impersonation loop'; for subjectPosition it clarifies why it's preferred over position; for importance it mentions clamping behavior; for space and position it explains auto-anchoring. This goes far beyond the schema's descriptions.

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 immediately states the core purpose: 'Persist one event to this agent's memory stream.' It clearly specifies the verb (persist), resource (event to memory stream), and distinguishes between different kinds of events (observation, action, chat, reflection) with specific behaviors. The warning about the chat speaker pitfall adds clarity that differentiates this tool from potential alternatives.

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 provides explicit guidance on when to use the tool (for persisting events) and how to use it based on kind. It states mandatory parameters for chat (speaker) and explains auto-anchoring behavior for observation/action vs. unanchored for chat/reflection. However, it does not explicitly mention alternatives among sibling tools, which would push it to a 5.

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

All space0 toolsInspect
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

A3.7/5.0
Disambiguation4/5

Most tools have clearly distinct purposes, with detailed descriptions differentiating them. However, the high count (60) introduces some overlap among memory-related tools (e.g., recall_nearby_memories, search_memories, recent_memory) and environment inspection tools (look_around, look_at, survey_site), causing minor ambiguity.

Naming Consistency4/5

The majority of tools follow a consistent verb_noun pattern (e.g., enter_space, create_commitment, recall_nearby_memories). A few names break pattern, like cognitive_boot (adjective_noun) or who_is_here (phrase), but overall the naming is predictable and readable.

Tool Count2/5

With 60 tools, the server exceeds the high end of the typical well-scoped range (3-15). While the domain is complex, many tools could be consolidated (e.g., multiple memory retrieval and building tools), making the surface feel bloated rather than lean and focused.

Completeness4/5

The tool set covers the core functionalities of the 3D world—spatial navigation, building, memory, commitments, skills, and social interaction—with few obvious gaps (e.g., no direct region deletion or agent interaction beyond chat). The breadth is appropriate for the domain, though some redundancy suggests minor over-engineering.

Resources