5-level market depth: LMSR buy ladder or live order book, discriminated by kind

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

Annotations already cover readOnly/idempotent/destructive/openWorld, so the bar is lower and the description still adds value: it distinguishes a simulated LMSR buy ladder from a live aggregated order-book snapshot and implies a point-in-time snapshot. It doesn't mention auth or rate-limit behavior, but the mode semantics are a genuine addition.

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, no waste, and the mode/discriminator detail is front-loaded before the routing hint to the sibling tool.

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?

An output schema exists, so return-value detail needn't be in the description; what's left — the two possible depth shapes and where to go for full depth — is exactly what an agent needs to call this correctly.

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 100%, so address/chainId semantics are already fully documented and the description adds nothing about them. The `kind` discriminator it mentions refers to the response shape rather than an input, so param-level value is baseline.

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+resource (market depth, 5 levels) and names the two modes it can return, discriminated by `kind`. It explicitly situates itself against the sibling problee_get_orderbook, so an agent can tell them apart 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?

Frames itself as the 'discovery-sized view' and routes full-depth consumers to problee_get_orderbook, which is clear context. It doesn't state an explicit when-not condition (e.g. when depth beyond 5 levels is unnecessary), but the alternative routing is unambiguous.

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