Skip to main content
Glama

tare_cache

Read-only

Analyze a session transcript to report context size, prompt-cache warmth, and the next message's cost warm versus cold.

Instructions

For one session transcript: context size, whether the prompt cache is still warm, and what the next message will cost warm versus cold.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "transcript_path": "<transcript_path>"
    },
    "name": "tare_cache"
  }
}

Input Schema

NameRequiredDescriptionDefault
transcript_pathYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

readOnlyHint=true already tells the agent this is a safe inspection. The description adds real substance beyond that: it discloses the three computed outputs (context size, warm/cold cache state, and comparative next-message cost), which is the key behavioral fact for an analysis tool with no output schema.

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?

A single front-loaded sentence with zero padding; every clause maps to a distinct output the agent will receive. No restructuring would make it shorter without losing information.

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 read-only, single-parameter tool with no output schema, the description covers input scope and the three return values, which is most of what an agent needs. It stops short on cost units/currency and on what 'still warm' depends on (recency window), minor gaps for the tool's low complexity.

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 0%, so the description must carry the parameter meaning — and it does partially, framing transcript_path as a single session transcript rather than a directory or ID. It does not say what form the path takes or whether it must be a raw transcript file, leaving format ambiguity.

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?

The description names the resource (one session transcript) and enumerates exactly what is reported: context size, cache warmth, and next-message cost warm vs. cold. That is far more specific than a restated name, but it never distinguishes this tool from the siblings tare_receipt and tare_wrapped, so an agent must infer the boundary.

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 only usage signal is the scoping phrase 'For one session transcript', which implies single-session analysis rather than aggregation. There is no explicit when-to-use, no when-not-to-use, and no reference to alternatives such as tare_receipt or tare_wrapped that an agent could route against.

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

Deploy Server

Other Tools