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

Annotations already declare destructiveHint=true, non-idempotent, and open-world, so the safety profile is known. The description still adds real context beyond them: market-order execution, reduce-only enforcement that cannot open or flip a position, third-party permission scoping, and that it works while trading is halted. It omits price-slippage or failure behavior, but with a rich annotation set that gap is minor.

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?

It is dense and front-loaded with the core action, and every clause carries information, but it is a single run-on block mixing purpose, semantics, permissions and a suggested next step. Slight structural cost, no wasted sentences.

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?

Output schema covers return values, so the description only needs to cover invocation context — and it does: mechanism, reduce-only guarantee, permission scoping, halt behavior, and a follow-up call (get_my_positions). Nothing needed to call it correctly is missing.

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 100%, so the schema already documents venue, symbol, size_base and close_fraction, making baseline 3 appropriate. The description adds only the either/or framing between close_fraction and size_base plus the '1 = all' shorthand, which is useful but marginal over the schema text.

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 (close), resource (perpetual futures position), scope (all or part), and execution mechanism (reduce-only market order). It explicitly distinguishes itself from cancel_order and names the sibling to use for the other case, so an agent can route without opening either 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 concrete use cases (take profit, cut a loss, reduce exposure, undo a filled order) and an explicit exclusion with the alternative named (not for cancelling resting orders; use cancel_order). It also states a precondition-style rule that third-party apps can only close positions they opened, which changes which calls are legal rather than just which are sensible.

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