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

With no annotations provided, the description carries the full burden and delivers: it discloses the return contents (spread in bp, taker/maker fee, posting value per side, round trip, ranking), the API-key requirement, and critically the interpretive warning that the value is the size of the prize, NOT the probability of winning it, explicitly stating fill probability is not estimated. This is exactly the kind of behavioral context that prevents misuse.

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 front-loaded with purpose and use cases, and nearly every sentence earns its place — especially the fill-probability warning and cross_vs_post routing. The statistics block with named coins and round-trip bp values is useful calibration for agents quoting numbers, but it is somewhat long and could be tightened without losing the fee-differential floor insight.

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?

Against a minimal 3-param schema with 0% description coverage and no annotations, this description is remarkably complete: it covers return values (even though an output schema exists), two of three parameters, authentication requirements, typical magnitude via statistics, a critical interpretation caveat, and sibling routing. Nothing an agent needs to select and invoke this tool correctly is missing.

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 0%, so the description must compensate. It documents coin ('ticker e.g. 'sol'') and notional_usd richly ('price the crossing side as the real walk down the book instead of half the spread'). However, the side parameter is left to inference — it is referenced only as 'per side' in the returns, not explained as an input. Strong compensation for most params with one 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?

The opening sentence states a specific comparison — POSTING a resting order vs CROSSING the spread, per venue, for a crypto perp — with an unambiguous verb and resource. It distinguishes itself from siblings by naming cross_vs_post as the complementary comparison and by framing its output (maker/taker fee economics) differently from siblings like route_order or post_map.

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 gives verbatim use cases ('should I use a limit order or market order', 'which venue should I quote on', 'maker vs taker') and explicitly routes the agent to cross_vs_post with the condition: the best venue to post on is frequently NOT the best venue to cross on. This is explicit when-to-use plus alternative selection, not left to inference.

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