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

Annotations already declare readOnly=false, destructive=true, idempotent=true, openWorld=true, so safety and repeat-call behavior are covered. The description adds a genuine behavioral fact not derivable from those hints: the answer terminates in an "interrupted" state rather than being deleted or silently discarded. It stops short of saying whether partial output is preserved.

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?

One front-loaded sentence carrying purpose, scope, and outcome, followed by a compact endpoint reference. No filler and nothing redundant.

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 single-parameter, no-output-schema action whose safety profile is fully covered by annotations, the description supplies enough to call it correctly. Minor gaps remain around error/edge behavior (calling when no answer is running) and whether partial results survive.

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 100%, and the sole parameter's own schema text is a bare restatement ("The chatId."). The description adds no format, source, or format-of-id detail beyond echoing the path template, so the baseline 3 applies.

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?

Specific verb ("Stop") plus a precise resource and scope ("the answer Muse is working on in a chat"), with the observable outcome in parentheses. It is unambiguous and clearly distinct from the delete_* / stop_browser siblings, though it does not name an alternative tool explicitly.

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 only implied by the verb: an agent can infer it applies while a generation is in flight. There is no statement of when not to use it, no prerequisites (e.g. an active answer must exist), and no routing against siblings such as muse_chat or muse_get_chat.

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