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

Annotations already cover safety (readOnly, idempotent, non-destructive), yet the description adds substantive behavioral caveats: the median round-trip figure only appears at 10+ touches, fees of 0.1% per side are deducted, and the output is explicitly 'not a win rate' and 'not a side'. Those interpretation constraints are exactly what an agent needs and cannot get from the schema.

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 text is short but structurally broken: sentence fragments ('Before the next order.', 'NO_TRADE.', 'Not a win rate. Not a side.') with missing subjects and no clear ordering. The most important information — what the tool actually computes — is buried in the middle rather than front-loaded, forcing re-reading.

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 an 8-parameter analytical tool with no output schema, the description does sketch the return payload (counts per outcome, closest touched day, permalink) and the sample-size gate. It leaves ambiguous whether the sub-10-touch case errors or returns a NO_TRADE verdict, and it never explains how pattern length or forward horizon affect results.

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 100%, so the baseline is 3. The description restates the required trio and their aliases, but the schema already documents 'Alias: level' and 'Do not take this from a band' on each property, so the description adds almost no meaning beyond structured fields. Nothing is said about how f, q, anchorTs or interval change the analysis.

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 core is discernible: given an entry level, invalidation and target, it searches similar historical candles and reports which price printed first. But the opening fragment 'Before the next order.' does not state a verb or resource, and the agent must reconstruct the purpose from the middle clause. No sibling is named, so nothing prevents confusion with evaluate_candle_hypothesis or get_trader_decision_v2.

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?

'Before the next order' is an implied timing cue, and 'Do not invent a missing price from P10, P90 or any band' is a useful input precondition. However there is no explicit when-not guidance, no routing to the many sibling analysis tools, and no statement of what to do when a required price is genuinely unavailable.

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