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

Annotations only give the safety profile (destructive=true), while the description discloses the full behavioral chain: it records the kept variant, ships it as the sole page version, removes experiment code in the same PR, writes a record_action entry under module EXPERIMENTS, and costs nothing. That is substantial side-effect context an agent cannot get from the annotations alone.

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-loads the core action ('Stop a test') then sequences the consequences in the order they occur. Compact overall, though the 'Free.' fragment and the internal 'record_action ... module EXPERIMENTS' reference are slightly jargony.

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 destructive, no-output-schema mutation with documentable params at 0% coverage, the description covers the important side effects and the key 'keep' semantic well. The remaining gap is the meaning of 'note' and 'site', which no structured field explains.

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 0% across 4 params, so the description carries the burden. It clarifies the 'keep' semantic ('the winner, or the control when nothing won'), which is genuinely useful, but leaves 'key', 'note', and 'site' unexplained. Partial compensation only.

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 action ('Stop a test') plus the concrete follow-on effects: record the kept variant, ship it as the page's only version, remove experiment code. This distinguishes it clearly from experiment_create and experiment_results without needing to open a schema.

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?

Usage is implied: call this when a test has concluded and you want to promote a winner/control. There is no explicit 'use this instead of X' or exclusion guidance, and the 'Free' note is a cost hint rather than a selection rule. Adequate but leaves the agent to infer the trigger condition.

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