ASTRA

tcai_capability_model

Read-onlyIdempotent

Query the expected valence for an action or list the learned capability table from an EMA-based action-to-outcome map.

Instructions

Agency capability model (DirectExperienceLearner port): action → expected-valence map (EMA). Query expected outcome of an action, or list the learned capability table.

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_capability_model"
  }
}

Input Schema

Name	Required	Description	Default
`action`	No	Action label to query expected valence for

Schema Changelog

Changes observed during successful MCP inspections.

First observedv3.1.0Sep 23, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds real domain context beyond that: the return is an EMA-derived action → expected-valence map from a DirectExperienceLearner port, telling the agent what kind of signal it gets back. It stops short of describing behavior for unknown/unseen actions.

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?

One compact sentence that front-loads the model name and mechanism before the two usage modes. The parenthetical '(DirectExperienceLearner port)' is dense jargon but does convey provenance in few characters; no wasted sentences.

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?

For a single-optional-parameter read-only query with no output schema, the description covers mechanism, both invocation modes, and the nature of the returned map, which is enough for correct invocation. Minor gap: it does not say what is returned for an action with no learned entry, and the no-argument list behavior is only implied.

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 description coverage is 100% and the single 'action' parameter is documented inline as the action label to query. The description's 'action → expected-valence map' phrasing reinforces intent but adds no format, casing, or vocabulary details beyond the schema, so baseline 3 applies.

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 mechanism and outcome: it exposes an agency capability model mapping actions to expected valence, and can either query one action or list the learned table. The dual mode is clear, though the definition never distinguishes itself from the many other tcai_* analysis tools in the sibling set.

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

Usage Guidelines3/5

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

The two modes ('Query expected outcome of an action, or list the learned capability table') implicitly tell the agent when to pass an action versus call with no argument. However, there is no explicit when-to-use guidance and no named alternative among the tcai_* siblings for related queries.

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

Deploy Server