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

Annotations already declare destructiveHint=true and openWorldHint=true, so the safety profile is covered; the description adds the mechanism the annotations cannot express: the tool returns an approval URL, never executes from chat, only the signed-in user can approve, and a pending request is not execution. It also discloses expiry and the structuredContent rendering behavior for native clients, which materially changes how an agent should report the result.

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?

Risk warning is correctly front-loaded and the confirmation/authorization flow follows in logical order. It runs long for a two-parameter tool, and the client-specific rendering paragraph (Codex/Claude/Cursor, Markdown link, card vs button) is agent-behavior coaching rather than tool semantics, though it is genuinely relevant to calling this tool correctly. A little redundancy around 'pending is not execution' could be tightened.

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, the description does the return-value work well: it explains the approvalUrl, structuredContent for native clients, expiry, and the status-check follow-up. The gap is parameter-level — for a destructive, high-stakes tool with 0% schema coverage, an agent still has to guess what idempotencyKey does and when to supply 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% for both parameters, so the description must carry the load and it largely does not. It gestures at 'target deployment' and 'broker mode' but never explains the deploymentId format or what idempotencyKey is for — the idempotencyKey parameter is never mentioned at all, despite the tool being idempotentHint=true, which makes that omission notable.

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 ('stops an existing BotSpot live deployment') and immediately scopes the blast radius ('changes a running trading system'). The word 'live' implicitly separates it from stop_backtest, and it names get_deployment_action_status as the follow-up tool, so an agent can place it correctly without opening 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?

Gives an explicit precondition ('Only call this tool after the user has explicitly confirmed the stop action, broker mode, and target deployment in the current conversation') and an explicit post-condition ('check get_deployment_action_status after approval'). It also states the negative case — chat-only approval and reusable grants do not execute — which is exactly the routing information an agent needs.

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