Fails-to-Deliver Data

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

Annotations supply only readOnlyHint=true, and the description adds substantial beyond-schema behavior: the balance-vs-flow nature of Quantity, the prior-close convention for Price, the covered-window semantics, publication lag, and what absence of a date does or does not mean. This is exactly the interpretive detail an agent needs for a data-quality-sensitive tool.

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?

Purpose and source are front-loaded, followed by field semantics and coverage caveats, with no filler sentences. It is dense and slightly long, but nearly every clause carries interpretive weight rather than restating the schema.

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 fully carries the burden: it defines the returned fields, their units and conventions, the valid date window, and the lag behavior. An agent can interpret results correctly without additional context.

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 100%, so ticker, startDate, endDate, and maxResults are already documented (including the max: 500 bound and the 'most recent N, oldest-to-newest' ordering). The description's detail concerns output fields (Quantity, Price, Value) rather than inputs, so it adds little input-level meaning beyond the schema; baseline 3 applies.

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 — 'Get fails-to-deliver (FTD) data for an exact listed stock or exchange-traded fund from the SEC's twice-monthly FTD files' — and pins the source and cadence. This clearly separates it from siblings like GetShortInterest or GetShortVolume.

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?

Gives clear interpretive context: never sum Quantity across dates, dates absent within the window mean no reported fails, earlier dates are only partially covered, and rows trail today by ~two weeks. It does not, however, name alternative tools (e.g., GetShortInterest) or state when to prefer one over the other, so it stops short of explicit routing.

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