search_orders

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

Annotations already declare readOnly/safe/openWorld, but the description adds substantive behavior: the API-enforced 30-day lookback cap, the 500-order return limit, and a cross-tool vocabulary warning that equityMarketSession (REGULAR/REST_OF_DAY/TWENTY_FOUR_HOURS) is a different enumeration from place_order's equity_market_session (CORE/EXTENDED/TWENTY_FOUR_HOURS) and must never be fed into the other. That mismatch warning is exactly the kind of context annotations cannot provide.

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?

Front-loaded with purpose, then limits, then result shape, then args — a clean and useful ordering with dense, non-padding prose. Minor deduction because the result-shape paragraph partially repeats what the output schema and get_order already convey, though the cross-tool comparability note keeps it largely earning its place.

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 an 8-parameter, 0%-covered search tool this leaves nothing an agent needs unresolved: window and result caps, filter combination semantics, per-parameter formats, and cross-tool enum hazards are all covered, and the output shape is described even though an output schema exists.

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%, so the description carries the full burden, and it does: every one of the 8 parameters is documented with allowed values (full status enum, BUY/SELL, security_type list, OPEN/CLOSE applicability), formats and examples (ISO 8601 with a sample timestamp, SYMBOL:TYPE syntax with three examples), and the account_id environment-variable fallback. This is well beyond the bare schema.

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?

The first sentence names a specific verb and resource ('Search the account's order history') plus a concrete scope (last 30 days, any status). It explicitly contrasts itself with get_orders ('returns only the open/active orders embedded in the portfolio snapshot') and with get_order's result shape, so an agent can distinguish it from siblings without opening schemas.

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?

States exactly when to use it (order-history queries covering filled/cancelled/rejected/expired/replaced orders), names the alternative tool it is not, and clarifies that all filters are optional, combine with AND, and that a no-filter call lists everything in the window. It also tells the agent when to narrow (risk of exceeding 500 results), which is actionable guidance rather than inference.

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