paper_trade

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

Adds real behavior beyond annotations: no live order is submitted, positions may go short and cash negative (arithmetic only), and fees/slippage are applied explicitly rather than inferred. The price is caller-supplied, which is an important behavioral fact. One tension: 'Idempotent' reads against idempotentHint=false, though it is defensible because idempotency_key is required and the guarantee is key-scoped rather than unconditional; the description could have said 'deduplicated per idempotency_key'.

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?

Three short sentences, front-loaded with the action, then invariants, then the safety caveat. No filler; each clause (same-currency, explicit fees/slippage, no live order, arithmetic-only shorts) carries distinct information.

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 9 parameters, 7 required, 11% schema coverage, and no output schema, the definition leaves gaps: what a successful call returns (fill record, updated position, new revision), what happens on a revision mismatch, and how symbol strings are formatted. The simulation-vs-live distinction and arithmetic-only caveat are covered, so the core behavior is present but the contract is incomplete.

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 only 11% (only account_id documented), so the description must carry weight. It clarifies price provenance ('caller-supplied same-currency'), that commission and slippage are explicit inputs, and that expected_revision/idempotency_key are guard parameters. However, it says nothing about the symbol format ('EXCHANGE:TICKER'), quantity side semantics, or units for commission/slippage_bps.

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 ('Simulate a market fill') plus the key scoping constraints (caller-supplied price, same-currency, explicit fees/slippage). An agent can tell this is a paper/simulation execution tool rather than a live order tool. It does not explicitly name a sibling (e.g. paper_mark_prices, replay_trade) to differentiate, so it stops short of a 5.

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 implied by 'simulate a market fill' — use it to book a hypothetical trade into a paper account — but there is no explicit when-to-use/when-not or routing to alternatives such as paper_mark_prices (for valuation only) or replay_trade (for replay-driven execution). No preconditions (account must exist, revision must match current state) are stated.

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