Per-Day Observation Status

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

Annotations already indicate readOnly, non-destructive, and idempotent, so the description doesn't need to repeat those. It adds valuable behavioral context: it discloses the honesty limits of the response's 'classification_limits' field, explaining that 'no_print' does not distinguish illiquid no-trade from suspension from missing data, and that 'pre_listing' is only asserted when a listing date is known. This goes beyond just the safety profile and provides critical interpretation guidance. It doesn't contradict annotations, but could have added more about rate limits or output structure, hence a 4 instead of 5.

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 fairly long but every sentence earns its place: it defines the purpose, gives usage guidance, and provides critical interpretation warnings. The front-loaded sentence clearly states the verb, resource, and output categories. The warning about zero returns is important, and the honesty limits are necessary for correct interpretation. The structure is effective—purpose first, then usage, then caveats. It is slightly verbose but not padded, so a 5 is justified given the complexity of the tool.

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 tool's complexity (multiple classification reasons, honesty limits) and the absence of an output schema, the description does an excellent job of covering what the agent needs to know to call it correctly and interpret results. It explains the classification values, the meaning of 'no_print', and the limitations of 'pre_listing'. However, it does not explicitly mention that the response will contain a classification for every day in the window, nor does it discuss pagination or response structure details, but those are minor gaps. The description is nearly complete for an agent to use the tool effectively, so a 4 is appropriate.

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 input schema already describes all four parameters with 100% coverage: `days`, `symbol`, `ticker`, and `identifier`. The description does not add new meaning to these parameters; it mentions 'lookback window' but doesn't elaborate on the parameters beyond what's in the schema. Since schema coverage is high, a baseline of 3 is correct. The description's value lies in the conceptual output classification, not in parameter semantics.

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's purpose: for each calendar day in a lookback window, it returns why a price is or is not present, enumerating the specific classification reasons (traded, weekend, holiday, etc.). It includes a concrete resource ('Per-Day Observation Status') and verb ('get'), making it distinct from the many sibling data getters, though it doesn't explicitly name a sibling. The level of specificity—explaining the exact output classifications—makes the tool's purpose unambiguous.

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 gives explicit guidance on when to use it: when a price series has gaps and the user needs to know whether a missing day was a market holiday, suspension, pre-listing, or genuinely missing. It also provides a strong 'when not to use' by warning that a missing price is NOT a zero return and should be treated as not-a-return, not 0%. Though it doesn't name a specific alternative sibling, it effectively tells the agent when this tool is the right choice (before computing returns over gappy series), which is more than sufficient.

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