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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile needs no restating. The description does add real behavioral value by disclosing that it always returns NO_TRADE and refuses to invent a price from P90/P10 — an anti-hallucination guarantee the schema cannot express. Beyond that, nothing is said about sample sizes, rate limits, or what the analysis actually returns, so it earns a solid but not rich score.

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 analytical question, then the gating rule, then the fallbacks — no filler sentences. The telegraphic fragments ('A level alone reports reach.', 'Always returns NO_TRADE.') are efficient but slightly clipped, and the crucial NO_TRADE disclosure sits at the very end where it is easiest to miss.

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 13 parameters, no output schema, and a genuinely complex research tool, the description covers inputs and gating behavior well but says almost nothing about the result shape beyond the NO_TRADE verdict and 'session profile'/'reach'. Since there is no output schema, a sentence describing what evidence is returned (analogue counts, hit rates, sample size) would close the remaining gap.

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 100%, so the baseline is 3; the description goes beyond it by explaining how three price parameters interact as a set (replay requires all three, level alone gives reach, level omitted gives session profile) rather than describing them individually. That interaction semantics is not derivable from the per-field schema text and directly changes how a caller composes arguments.

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 and object ('Test whether a candle window behaves differently') and enumerates the exact conditioning dimensions: UTC sessions, UTC event hour, weekday/weekend, volatility regime. An agent knows precisely what analytical question this answers, though no sibling tool is named (e.g. evaluate_candle_hypothesis or replay_candle_hypothesis), so differentiation is only implicit.

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 conditional logic: a price order is replayed only when levelPrice, targetPrice and invalidationPrice are all supplied; omitting level yields the session profile; a level alone reports reach. This is genuine when-to-use guidance for parameter combinations, but it never names an alternative tool or an exclusion condition against siblings, 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.