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

With no annotations, the description carries the full burden and does a solid job: it reveals series ordering (newest-last), the latest=true single-row map, the default window behavior when start/end are omitted, the lagged quarterly archive, and automatic ticker-to-internal-key resolution. It doesn't mention rate limits, errors, or data coverage, but it provides substantial non-obvious behavior context.

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 description is a single dense paragraph, but every sentence contributes distinct value: content definition, usage guidance, return behavior, and ticker resolution. It is well-structured and appropriately sized for the tool's complexity, though a bit dense for quick parsing.

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?

The description covers the full factor list, data grain, return formats (series vs. map), default window behavior, and ticker resolution. For a tool with no output schema and no annotations, it gives a strong picture of expected results and edge cases. It doesn't detail the exact JSON shape of the series, but the description is nonetheless quite complete.

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 description coverage is only 20% (only ticker has a description, and it just says required). The description adds meaning for 'latest' (single-row map) and start/end (default window behavior), but it does not explain the 'limit' parameter or the expected date format for start/end. It partially compensates for the schema gap but leaves several parameters semantically unaddressed.

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 states the tool provides a compact 13-factor predictor panel for one stock, enumerating the specific accounting anomalies (Sloan accruals, asset growth, gross profitability, etc.). It also distinguishes it from the full ~460-column factor panel, which differentiates it from sibling tools and identifies the exact resource being served.

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?

The description explicitly says to call it for a ready-made feature vector when you don't need the full ~460-column factor panel, providing clear when-to-use context with an implied alternative. It also explains behaviors for no start/end and the latest=true flag, but it does not name sibling tools directly or elaborate on when to avoid this tool.

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