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

Annotations cover the safety profile (readOnly, non-destructive, open-world), and the description adds genuinely non-obvious behavior: a 10-symbol cap, that it reports conditions only and never reads entry or size, and that unauthenticated calls return a PaymentRequired object rather than data. The idempotentHint=false is not explained, but the added behavioral context is substantial.

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-loads the core purpose, then qualifies scope and access. The output enumeration is dense but each item is informative, and there is little wasted text. Slightly list-heavy for a four-sentence description.

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 usefully enumerates the returned condition fields and explains the payment-gated failure mode, which an agent needs to interpret an empty response. Rate limits and pagination are not addressed, but the tool is a single capped read.

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% and the single symbol parameter is fully documented there, so the baseline is 3. The description's 'up to 10 symbols per call' reinforces the batch limit but adds no new syntax beyond the 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?

States a specific verb (read), resource (hold state), and scope (live intraday SELL-SIDE, names you already hold), then enumerates the exact outputs. It is clearly distinguishable from the non-live sibling get_hold_state and from buy-side reads like get_buy_list_live.

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?

Explains the access conditions an agent must know before calling: a Coil Live subscription (7-day trial), an x402 wallet for pay-per-call, or a PaymentRequired response with no data. It does not explicitly state when to prefer the non-live get_hold_state over this one, so routing between the two is left implicit.

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