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

Annotations already declare destructiveHint=true, idempotentHint=false, and openWorldHint=true, so the safety burden is partly carried. The description adds genuine context beyond them: execution always occurs at the server's price (no price control despite a price parameter), stocks are long only, and intraday stock entries require the market to be open. It does not disclose what a close/reduce destroys, whether actions are reversible, or the result shape, which matters for a destructive tool.

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?

Two sentences, front-loaded with the core verb and resource, and the action list is compacted into a single enumeration. No filler, though the action list inside the first sentence makes it slightly dense to scan.

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 13-parameter destructive mutation with no output schema, the description covers the essential constraints (long-only, market-open requirement, server-side pricing) but leaves gaps: no success/return behavior, no mention of what happens to an existing position on open versus add, and no error-path guidance. Adequate to call correctly, not complete for confident use.

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 62% across 13 parameters, so the schema documents the tricky fields (fraction, price, timeframe, expires_in, idempotency_key) itself. The description adds only one real constraint on parameters — the long-only restriction on side — and says nothing about how quantity versus notional_usd interact or which fields apply to which action beyond what the enum descriptions already say.

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 ('Change the autopilot's paper position by hand') and enumerates the nine actions the tool accepts, which lets an agent distinguish it from lifecycle siblings like start_autopilot or stop_autopilot. Minor ambiguity because set_timeframe and cancel_order are named as 'position changes' when they are not strictly position mutations.

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 real preconditions: 'always at the server's price', 'Stocks are long only', and 'intraday stock entries need the market open'. These tell the agent when a call is valid, but there is no explicit guidance on when to use this manual action versus run_autopilot_agent or update_autopilot, so the manual-override intent has to be inferred.

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