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

With only readOnlyHint=true in annotations, the parameter text adds substantial behavioral context: candle-read performance (35 docs/110 kB/163 ms vs 389 docs/1169 kB/356 ms), a 20 s live-quote fan-out budget with fallback to daily closes so the scan 'cannot hang the response,' and the ~$0.05 per-anomaly Sonnet 4.6 cost when synthesis is enabled. This meaningfully exceeds the annotation's coverage.

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 main description is a single efficient sentence, but it is terse to the point of under-specification. Meanwhile the symbolsScope parameter description is overloaded: it embeds a historical before/after narrative, a cost measurement, and an anecdote about the ten largest moves, which could be restructured into the current semantics plus a cost warning. Structure is uneven.

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 a 4-parameter tool with no output schema and many sibling scanners, the definition does not state the return shape: fields per flagged anomaly, ordering, limits, or the detection time window (intraday vs end-of-day; the daily-closes fallback hints at candle-based detection but never states it). The parameter descriptions partially compensate by disclosing returned market context and the synthesis text per anomaly, but entry-level return semantics are left to inference.

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%: all four parameters have descriptions with defaults, enums, and effect explanations. The tool-level description adds no parameter info, so the baseline 3 applies — the schema does the heavy lifting. The parameter descriptions are unusually rich (especially symbolsScope), but that richness is inside the schema, not additional value from the description.

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 description states a specific verb+resource: automatically catching price moves that deviate from a company's usual volatility. This is clear about what the tool computes. However, it does not differentiate it from near-neighbor siblings such as find_overheat_candidates, find_dip_candidates, whats_moving_now, or run_predictive_scan, all of which plausibly do similar scanning.

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?

Usage is only implied: if you want volatility-deviation anomalies, run this scan. The parameter descriptions offer operational tuning guidance (sigmaThreshold: 'Use 2 for stricter, 1 for noisier'; symbolsScope: cost and universe implications), but there is no explicit statement of when to prefer this tool over the many sibling anomaly/opportunity scanners, and no exclusions.

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