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

Annotations already cover read-only, idempotent, non-destructive and closed-world, so the safety profile is settled. The description adds genuinely new behavioral context: the output is identical for every reader, calls refresh nightly over a 14-day window, and the answer must carry the not-advice line and run date — a disclosure obligation an agent would otherwise miss.

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?

Two sentences, front-loaded with what the tool returns before the when-to-use guidance, and no filler. The first sentence is dense with stacked clauses (nightly call, change flag, for/against insights, track record), which slows scanning slightly but each clause carries real 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?

With one required parameter, full schema coverage, an output schema, and rich annotations, the description covers the remaining gaps: input flexibility, the 2–5 bound, freshness, and the required disclaimer. Nothing an agent needs to call this correctly is missing.

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 coverage is 100% and the sole parameter's description already states 'two to five US stocks, each by symbol (NVDA, BRK.B) or company name (Nvidia)', including the maxItems and dotted-ticker example. The description's 'by symbol or company name' restates that rather than extending it, so the baseline 3 applies.

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 verb and resource — StockMap's published calls on two to five US stocks side by side — and immediately scopes the output (nightly 14-day call, change flag, insights for/against, track record). The 'two to five' framing plus 'side by side' cleanly separates it from the single-stock sibling stock_call.

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?

It gives a clear trigger: 'Use it when someone asks how two to five US stocks stack up against each other, or which of them the model's calls read stronger, whether or not they name StockMap.' That handles the ambiguous-request case well, but it never names the sibling to use for a single stock, so the exclusion at the 1-stock boundary is left to inference.

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