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

Beyond the readOnlyHint annotation, the description discloses critical behavioral traits: the `degraded: true` flag indicating an incomplete/stale list, the requirement not to cache it, and the contract `count === len(assets)`. It also reveals the shared cache mirror, adding valuable operational context not captured in annotations.

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?

The description is dense but well-structured: it starts with the purpose, then gives usage guidance, and then details the contract and edge cases. Every sentence earns its place, with no redundant words or filler.

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 a 0-parameter tool with no output schema, the description fully covers the behavioral contract, usage context, and data quality flags. It leaves no meaningful gaps for an agent to discover by trial and error.

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?

The tool has no parameters, so the schema carries no burden. The description adds meaning by explaining the response contract and degraded state, effectively covering what the tool returns. Baseline for 0 params is 4, and this is met.

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 description states the tool returns the asset universe that check_trade, get_trade_plan, and get_levels can price, explicitly naming the sibling tools it supports. It uses a specific verb and resource, and clearly differentiates its role as a one-time discovery call rather than a pricing or analysis tool.

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 explicit: 'Call once instead of discovering support by error' directs the agent to invoke this tool before pricing tools. It also provides handling guidance for the degraded flag (do not cache, retry later) and notes the shared cache mirror, offering clear context on when and how to use.

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