profile_stop

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

With no annotations, the description carries the full behavioral burden and does so well: it discloses what survives (cookies and login state in identity storage), what is lost (form input), idempotency (no-op on an already-idle identity), the two distinct things that may be running and the ordering of shutdown, plus the two failure modes (unknown identity, daemon not running). This is exactly the context an agent needs before invoking a destructive-ish operation.

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?

Well front-loaded: the core action and the state-survival rule come first, followed by the two-things-running explanation, then Args/Returns/Fails. It runs a bit long and the session-vs-identity fallback sentence is dense, but nearly every sentence adds actionable information rather than restating the name.

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?

No output schema exists, so the description supplies return semantics itself, defining the `stopped` and `closed` fields and the already-idle case. Combined with explicit failure conditions and side-effect disclosure, an agent has everything needed to call this correctly without further exploration.

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%, so the description must compensate; it names the sole parameter and specifies its provenance ('exactly as profiles_list reports it'), which tells the agent where to obtain a valid value. It could have added case/normalization rules, but the sibling pointer covers the main risk.

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+resource (stop an identity's browser) and immediately qualifies scope with 'however it was started', which distinguishes it from profile_start and the session_* tools. The second paragraph clarifies that it closes either the daemon-driven warm session or a desktop-launched window, so there is no ambiguity about what object is being acted on.

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?

Gives clear positive guidance ('Stop identities you are done with') and explains why, plus the operational rationale that an idle identity frees the warm browser. It does not contrast with profile_delete or profile_restore in the sibling list, so the agent must infer that stopping is not the same as deleting/trashing — a small but real gap.

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