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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, so the remaining burden is light. The description adds real semantics beyond that: pct is signed with '-10 = a fall of 10% or more', and days is measured in trading days with an omission rule ('a fall without days = from its high'). It does not say what the result contains, but the safety profile is fully covered.

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?

Index options and the pct/days semantics come first, and the example queries close it out, so it is well front-loaded with no filler sentences. It is dense and parenthetical-heavy enough to read as a run-on, but every clause carries information.

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 five-parameter analytical tool with no output schema, the description explains how to trigger the study but not what comes back (forward returns, distributions, hit rates) nor what symbol does. An agent could invoke it correctly, but would be guessing about both one input and the response shape.

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?

With 0% schema description coverage, the description must carry the semantics and it largely does: pct's sign convention and threshold meaning, days as trading days plus the default behavior when omitted, all three index enum values expanded, and market illustrated via '(market HK)'. The fifth parameter, symbol (maxLength 300), is never mentioned, leaving a real 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 description names the operation concretely ('like event_study, for a move of an index') and enumerates the exact index set (SPY/S&P 500, QQQ/Nasdaq-100, HSI/Hang Seng), so an agent knows this computes post-move behavior rather than raw prices. It differentiates from event_study by analogy but never spells out the distinction in words.

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?

Two natural-language example queries ('what happens if the Nasdaq drops 10% in two days', 'what does Hong Kong do after the S&P 500 falls 3% in a day (market HK)') give concrete when-to-use context, including the cross-market case. There is no explicit exclusion or statement of when to prefer event_study or check_stocks instead.

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