Stop the background log

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

With no annotations, the description carries the full burden and does well: it discloses a non-obvious cross-session side effect (stopping a log or live started in a terminal or another client when `job` is omitted) and explains the already_ended flag semantics, including that the summary is stale in that case. It does not cover failure modes, whether the log file is retained, or permission requirements, keeping it short of a 5.

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?

Front-loaded with the action and return payload, then the conditional behavior and edge case. The parentheticals are dense but each clause carries information; the second sentence runs long and could be split for readability, but there is no filler.

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?

With no output schema and no annotations, the description supplies the return fields inline and covers the default-path behavior and the already-ended edge case, which is what an agent needs to call it correctly. Missing only error behavior when no log exists and whether data is preserved after stopping.

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 coverage is already 100% for the single `job` parameter, so the baseline is 3. The description earns above baseline by explaining the consequence of omitting `job` — it will reach out and stop a log started elsewhere, not merely default to the latest one — which is meaning the schema does not convey.

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 specific verb and resource ('Stop the background log') and immediately enumerates what comes back (file, records, duration, min/max/mean per unit, link gaps). This is clearly distinguishable from log_start, log_status, and live, which would start, inspect, or stream rather than terminate and summarize.

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?

The description makes the primary use case clear (terminate a running log and get its summary) and adds a useful conditional: without `job` it will also stop a log or live started elsewhere. It stops short of explicit routing guidance such as 'use log_status to inspect without stopping' or stating what happens when nothing is running, so there is context but no exclusions.

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