ASTRA

tcai_memory_retrieve

Read-onlyIdempotent

Retrieve ranked memories by blending cosine similarity, PAD emotional congruence, and salience, so AI assistants can find relevant past context.

Instructions

Retrieve memories by blended cosine similarity, PAD congruence and salience

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "tcai_memory_retrieve"
  }
}

Input Schema

Name	Required	Description
`topK`	No
`arousal`	No	Arousal ∈ [0,1]
`valence`	No	Pleasure ∈ [−1,1]
`dominance`	No	Dominance ∈ [0,1]
`embedding`	No	Query vector (defaults to current broadcast)

Schema Changelog

Changes observed during successful MCP inspections.

First observedv3.1.0Sep 23, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds that ranking is a weighted blend of three signals, which is useful, but says nothing about result shape, whether an empty query embedding falls back to the current broadcast, or ordering guarantees.

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?

A single front-loaded sentence with zero filler, and the mechanism is stated up front. It is arguably too terse for a 5-parameter retrieval tool, but nothing in it is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description should describe what comes back or how topK shapes results, and it does not; nor does it clarify the relationship to tcai_memory_store or the embedding-default behavior. Adequate for identification, incomplete for confident invocation of a system this complex.

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 80% and the schema already documents embedding, valence, arousal and dominance ranges; topK is undocumented in both places. The description's mention of cosine similarity and PAD congruence loosely maps to embedding and the PAD triple but adds no syntax or default behavior, matching the baseline 3 for a well-covered schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Retrieve) and resource (memories) and even names the ranking mechanism (blended cosine similarity, PAD congruence, salience), which is unusually informative for a one-liner. It never explicitly distinguishes itself from the sibling tcai_memory_store, so it falls short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains how memories are scored but gives no guidance on when to call this versus alternatives such as tcai_memory_store or other tcai_* context tools, and no prerequisites or exclusions. Usage is only inferable from the tool name and scoring detail.

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

Deploy Server