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

While annotations cover safety hints (readOnly), the description adds rich behavioral details, such as specifying that 'a later restatement stays visible rather than replacing the original' and that 'Days the market was shut are absent, not zero-filled.' This context is vital for data interpretation.

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?

Although dense, the description is highly efficient. Each sentence serves a distinct purpose: defining the source, stating the value proposition, differentiating from siblings, explaining data integrity, and listing hard limits.

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?

Given the complexity of being a high-volume, archival, bulk-data retrieval tool, the description is maximally complete. It covers data integrity, performance implications relative to siblings, and hard constraints (366 days / 10k limit).

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 100% schema coverage, the baseline is high. The description adds semantic value by explaining how the parameters lead to a high-density, aggregated output format rather than a one-to-one retrieval, which helps the agent understand the resultant data structure.

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 clearly defines the tool's purpose as retrieving daily closes from an immutable archive. Crucially, it distinguishes itself by specifying it provides 'N symbols by M days in one call,' setting it apart from tools that require one call per holding.

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 provides an ideal use case ('shape a portfolio backtest actually needs') and explicitly defines when *not* to use it by referencing alternative sibling tools that would require multiple, inefficient calls.

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