Bandingkan saham

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered; the description adds real behavior beyond that by disclosing the sort key (totalReturnPct incl. dividends when available for all, else priceReturnPct) and instructing the agent to surface rankedBy to the user. It stops short of covering failure modes such as invalid or non-IDX tickers.

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?

Three tight sentences: what it does and its scope first, then the ranking rule, then the user-facing obligation. No filler, no repetition, and the most decision-relevant fact (ranked by total return when available) is front-loaded.

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, the description usefully names the return fields (totalReturnPct, priceReturnPct, rankedBy) an agent will need to interpret results, and annotations cover safety. Remaining gaps are minor for a two-parameter read tool: error behavior for out-of-range ticker counts or unknown symbols.

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 50%: tickers is documented in the schema, range is not (it carries only an enum and default). The description restates the 2–10 bound and clarifies that one range applies uniformly across all compared tickers, but adds no format or syntax detail for ticker codes beyond the schema example.

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 and resource ('Bandingkan performa'), plus hard scope limits: 2–10 tickers, IDX stocks and/or IHSG, single shared time range. Those constraints (multi-ticker, bounded count) inherently separate it from the single-ticker siblings get_quote and get_history.

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 implied by the scope statement (use this when comparing several stocks over one range) but never stated as guidance. No alternative is named — nothing tells the agent why to pick this over calling get_history repeatedly, nor what happens if only one ticker is supplied.

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