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

The annotations already declare readOnlyHint=true, so the description does not need to repeat that safety profile. Beyond that, it discloses two real behaviors the agent could not otherwise infer: that results follow the request order, and that unknown symbols return found=false rather than failing the whole call. It does not cover pagination, and for a batch read the cost or latency per symbol, but the partial-failure semantics are the important part.

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 English text is front-loaded with the returned fields, then the alternative tool, the behavior, and the date format — every sentence earns its place. The main cost is the full Japanese restatement, which roughly doubles the length; however, that serves a localization purpose, and the structure remains scannable.

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?

This is a one-parameter batch read with no output schema, and the description still specifies the returned fields, the ordering guarantee, the handling of unknown symbols, and the ISO 8601 UTC format with a Japan-time conversion note. Nothing an agent needs in order to call it correctly and interpret the result 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?

The schema description coverage is 100%, so the parameter's comma-separated 4-digit code format and 50-symbol cap are already documented and the baseline would be a 3. The description adds value by tying the found=false behavior to the symbols the caller submits, which tells the agent how to map output back to input, along with the hard limit of 50, so it earns a 4 rather than the baseline.

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: it retrieves the latest price, price date, change percentages and market cap for up to 50 companies in one call, and it explicitly states that these are the same fields as get_quote. It also distinguishes itself from the sibling get_batch_key_metrics_latest, so an agent can select the correct tool without opening either 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?

It states both when to use this tool ("Prefer this over repeated get_quote calls when comparing a list") and which tool to use instead when different fields are needed ("For PER, dividend yield and CAGRs of a list use get_batch_key_metrics_latest"). This explicit routing and its exclusions leave nothing to inference.

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