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

With only readOnlyHint=true in annotations, the description carries the full behavioral burden and does so richly: oldest-first ordering, reporting lag, as_of being the settlement date not today, honest-empty for unpublished tickers, and DATA_UNAVAILABLE refusal on an unreachable store. It also declares source and that it is free.

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?

Front-loaded with the core identity and return shape before the caveats, and every clause (ordering, units, lag, empty/refusal behavior) carries information. Some phrasing is dense and slightly redundant, but there is little pure filler.

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 must describe returns itself, and it does: names the top-level fields and specifies each point as exactly {date, shortPct}, explicitly excluding share counts and days-to-cover. Edge-case behavior is also covered, leaving nothing an agent needs to call it correctly.

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 coverage is 100%, so both parameters are already documented. The description largely repeats the schema ('default 6, max 26') but adds interpretation by translating max 26 into 'about one year', which is marginal added meaning over the structured field.

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+resource: the FINRA biweekly settlement-date short-percent series for one ticker. No sibling covers short interest (get_fails_to_deliver and ol_cftc_cot are adjacent but distinct datasets), and the description pins down the exact series, ordering and unit.

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?

Usage is implied clearly (trend of short interest for one ticker), and it usefully warns this is a lagged fortnightly snapshot rather than a live short-float figure. However it never states when to reach for this tool vs an alternative, nor names a sibling, so routing guidance is only implicit.

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