compare_price_performance

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

Annotations already cover read-only/idempotent/no-destruction, yet the description adds substantial behavior beyond them: Yahoo daily split-adjusted closes with dividends excluded (price return, not total return), per-symbol error isolation, a 260-point cap with weekly downsampling on long windows, and the provisional-last-point lifecycle (today's trades vs confirmed close, after-hours never becoming a point). That is exactly the mutation/freshness context annotations cannot express.

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?

Purpose and the headline workflow are front-loaded, and nearly every sentence carries non-redundant, decision-relevant detail. It is nonetheless a single dense block of several hundred words mixing window rules, sampling, provisional points and output formatting, which makes scanning harder than it needs to be.

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 9-parameter, read-only calculation tool with an output schema, the description covers everything an agent needs: symbol formats and aliases, window selection, benchmark requirements, currency handling, error isolation, and even what the text response contains (one-line summary plus compact JSON mirroring structuredContent). Nothing decision-critical is 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?

With 78% schema coverage the schema already names parameters, but the description supplies the semantics the schema lacks: what each of the four metric values means (base-100 normalization, symbol/benchmark ratio, return minus benchmark in %p), which metrics require a benchmark, symbol alias resolution (005930 tries .KS then .KQ), the period vs start/end vs trading_days alternatives, and how currency conversion is performed (Yahoo KRW=X same-date close).

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 (compare), resource (daily price performance) and hard scope (1-8 US/Korean stocks, ETFs or indices on one common trading calendar). It also differentiates itself from generic price-history siblings by explaining that it uses the KOSPI index itself rather than an ETF proxy and aligns cross-market calendars, so an agent can tell it apart without opening the schema.

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 an explicit end-to-end usage recipe ('get holdings from investmcp get_holdings, then call this once with their symbols ... and benchmark KOSPI (or SPY/^GSPC)') and states when to prefer it ('cross-market price history and index levels'). It also routes within the tool: if relative strength is requested without a benchmark, it says what happens and what to pass instead.

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