Skip to main content
Glama

tare_wrapped

Read-only

Analyze local coding-agent session logs to reveal token and spend breakdowns, plan-limit use, context fill, cache rebuilds, and actionable cost-saving fixes.

Instructions

Where this machine's coding-agent tokens and money went (Claude Code, Codex CLI, Gemini CLI, Cline, Roo Code, Kilo Code): API-equivalent spend, plan-limit use, what filled the context, cache rebuilds, highlights and the top fixes with estimated savings. Local and free.

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": "tare_wrapped"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNoWindow in days; 0 for all time. Default 30.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior3/5

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

readOnlyHint=true is already supplied, so the safety profile is covered by structured data. The description does add context beyond that: it discloses the data sources (local coding-agent logs across six named agents) and that the operation is 'local and free', meaning no network calls or billing. It does not say whether prior collection/indexing is required for results to be complete, nor how expensive the scan is on large log histories.

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?

The core scope ('where this machine's tokens and money went') is front-loaded, and the tool list plus report contents follow as compact qualifiers. The single dense sentence gets long mid-way with the six-product enumeration, but each clause adds differentiating information. Little waste overall.

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 readOnlyHint supplied, no output schema, and one fully documented parameter, the description covers the essentials of what the report contains. It remains silent on the two things an agent would still want: how this differs from tare_receipt and tare_cache, and whether any prerequisite data collection must happen first. Adequate, but leaves real gaps for a tool with two close siblings.

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%, so the single `days` parameter is fully documented in the schema, including the default of 30 and the 0-means-all-time convention. The description never touches the time window, so it contributes nothing beyond the schema. Baseline of 3 applies when the schema does all the work.

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 precisely: a spend/usage report over this machine's coding-agent logs (Claude Code, Codex CLI, Gemini CLI, Cline, Roo Code, Kilo Code), and enumerates what the report contains (API-equivalent spend, plan-limit use, context fill, cache rebuilds, fixes). An agent can tell it produces an aggregated cost report rather than raw events. However, it never states what distinguishes it from siblings tare_cache and tare_receipt, and the framing is a noun phrase rather than a verb+resource statement.

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?

There is no when-to-use or when-not-to-use guidance and no alternative tool is named; the sibling tools tare_cache and tare_receipt are never mentioned. 'Local and free' implies it can be called liberally without cost or privacy risk, but that is a property, not a selection rule. The agent must infer from the name alone whether to reach for this or a receipt/cache tool.

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