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

With no annotations, the description carries the behavioral disclosure burden. It explains the measurement approach (narrow band around each venue's own mid), the source limitation (only innermost levels), and warns against extrapolation. It does not cover auth, rate limits, or return envelope, which are less critical for this kind of read-only data tool.

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 tight paragraphs: definition, metric detail, limitation. No filler, and the critical negative scope is placed as a deliberate boundary. Every sentence adds 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?

For a read-only data tool without an output schema, the description is unusually complete about the content and limitations. It falls short only by not explaining the `minutes` parameter or the exact structure of the returned per-minute history, so an agent may still be uncertain how to set the sole argument.

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 schema documentation coverage is 0% and the description never mentions the only input, `minutes`. An agent must infer that `minutes` controls lookback or history length from context; the description adds no explicit meaning beyond the schema. With one simple optional parameter this is not fatal, but it is a real gap.

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 object ('cross-venue order book microstructure'), the assets (BTC, ETH, SOL), and enumerates the exact metrics returned: spread in bps, immediately-executable depth, bid share, basis, and per-minute spread history. The negative scope statement also makes clear what the tool is not, helping distinguish it from extrapolative market-impact queries.

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?

The description provides clear context for when the tool is relevant and explicitly states a when-not: it does not answer 'what moves price 0.5%' because streams only carry innermost levels. It does not, however, name a specific sibling alternative or list conditions that should route an agent to another tool.

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