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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds interpretation-critical context the annotations cannot: the band is narrow enough that every venue's stream captured it, each venue is measured around its own mid, and only innermost levels are present, which bounds what the numbers can be used for. No return format or pagination/limit detail is given, so not a 5.

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 the resource and venue scope, then the per-venue metrics, then the limitation, in three tight blocks. Every clause carries information: the measurement basis and the extrapolation warning both change how an agent interprets results.

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 and only one optional parameter, the description does the heavy lifting well by describing the returned fields and the measurement methodology. The main residual gap is that nothing states the response shape (per-venue keyed object vs list) or how the per-minute history is structured, which matters for a multi-venue aggregate.

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?

There is a single optional parameter with 100% schema description coverage, so the schema already explains the look-back window. The description never mentions the minutes window; the closest signal is 'per-minute spread history', which implies granularity rather than the look-back semantics. Baseline 3 applies since the schema carries the burden.

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 opening sentence names a specific resource and scope: cross-venue order book microstructure for BTC, ETH and SOL. The following sentences enumerate exactly what is returned per venue (spread in bps, executable depth in USD, bid share, basis, per-minute spread history), so an agent can tell precisely what the tool produces. It does not name or contrast any sibling such as get_orderbook_heatmap, which keeps it short of a 5.

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?

There is one explicit negative case: it does not answer 'what moves price 0.5%' because only innermost levels are carried. That is a genuine when-not, but there is no positive statement of when to reach for this tool and no named alternative among the many market-data siblings, so selection still requires inference.

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