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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered elsewhere. The description adds genuinely useful context beyond that — the credit cost and the free-tier ceiling of 25 calls/day — which an agent needs for budgeting. It stops short of explaining ordering, pagination beyond limit, or whether the 3–25% band is fixed or overridden by max_drawdown_pct.

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 screening criteria come first, then the return fields, then the cost — a sensible front-loaded order with no filler sentences. The middle sentence is a laundry list of metrics, which is dense but arguably earns its place since no output schema exists.

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 no output schema, enumerating the returned metrics (1/3/5/7/10-year returns, 10- and 20-year CAGR, volatility, dividend yield, DNA score) is exactly the right compensation, and the credit/rate-limit disclosure covers operational cost. The only real gap is the unresolved interaction between the stated 3–25% band and the max_drawdown_pct parameter.

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?

All four parameters carry schema descriptions, so the baseline is 3 and the schema carries the weight. The description does add the 3–25% band that shadows max_drawdown_pct, but rather than clarifying the parameter it introduces ambiguity about whether that band is a hard-coded floor or a default the parameter can widen.

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 a specific resource and screen — stocks with 15+ years of ≥7%/yr returns and ≥60% positive years that are 3–25% below their all-time high — so an agent knows exactly what population this returns. It does not, however, contrast itself with sibling tools like stock_dna or rank_dna (single-stock lookups), leaving the agent to infer that this is the list-level screener.

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 through the screening criteria: an agent can deduce this is the right tool when it wants a list of quality names in drawdown. There is no explicit statement of when to prefer this over siblings, no note on what happens when no stocks match, and no guidance on combining filters.

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