Log token, cost, and time usage per agent or project to track AI work and estimate costs when not provided.
Log tokens/cost/time you spent (cost estimated from the price table when omitted).
| Name | Required | Description | Default |
|---|---|---|---|
| cost | No | ||
| note | No | ||
| agent | No | ||
| model | No | ||
| job_id | No | ||
| api_key | No | ||
| project | No | ||
| seconds | No | ||
| tokens_in | No | ||
| subtask_id | No | ||
| tokens_out | No |
Changes observed during successful MCP inspections.
v0.36.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and only discloses one trait: cost is estimated from a price table when omitted. It says nothing about authentication (an api_key parameter exists), idempotency, whether repeated reports double-count, or what happens to unspecified fields, which is a significant gap for an 11-parameter mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single dense sentence with no filler, and the key fallback behavior (cost estimation) is placed in a parenthetical immediately after the main action. Nothing is wasted.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 11 optional parameters, no annotations, and no output schema, the description is markedly under-specified. It omits required-vs-optional expectations, whether api_key is mandatory, and the relationship between job_id/subtask_id and other tracking tools, so an agent cannot confidently invoke it.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% across 11 parameters, so the description must compensate and largely does not. It maps 'tokens' and 'time' loosely to tokens_in/tokens_out and seconds and explains the cost fallback, but agent, model, job_id, subtask_id, project, note, and api_key are left entirely unexplained.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a clear verb ('Log') and the resource being logged (tokens/cost/time you spent), so an agent immediately knows this records usage data. It does not differentiate from any sibling, but the siblings listed (msg_send, board, heartbeat, etc.) are obviously unrelated, so the gap is minor.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no statement of when to call this versus alternatives, whether it should be called per-task or per-turn, or any prerequisites. The mention of the price table is a behavior detail, not usage guidance. The agent must infer timing and cadence entirely.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.