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

Annotations already declare readOnly, idempotent, non-destructive and openWorld. The description adds real behavioral value on top: the source is in-memory hence cheap to poll, direction is the TAKER's side (a subtle semantic that changes interpretation), and each row carries a transaction hash. No rate limits or pagination behavior are mentioned.

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-loads what the feed contains, then direction semantics, then continuation and cost. Every sentence carries information, though the explicit field enumeration is slightly list-like and could be trimmed.

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, the description does the work of describing return fields, the flow24h aggregate and the latestId cursor, which is exactly what an agent needs. It leaves minor gaps around what 'limit' bounds in the combined two-market feed and how the 24h flow is bucketed.

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 coverage is 50%: 'asset' and 'since' are documented in the schema, and the description usefully reinforces 'since' as the latestId continuation token. 'limit' and 'venue' get no prose explanation, though the venue enum is self-describing. This is the baseline 3 given the mixed coverage.

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: the most recent trades across QX and QSwap in one newest-first feed, with the exact columns returned. That is clearly separable from siblings like qmax_get_candles, qmax_get_order_book and qmax_get_flow (though the embedded 'flow24h' summary is a useful distinguishing note).

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?

Gives clear operating context: served from memory so cheap to poll, and pass 'latestId' back as 'since' to fetch only newer rows — a precise incremental-polling recipe. It never names an alternative tool or states when not to use this one, so it stops short of a 5.

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