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

Annotations cover read-only and non-destructive safety, but the description adds valuable behavioral context: the score's peer-relative nature, that liquidity floors filter without altering scores, the exclusion of certain trusts, and that single-ticker lookups ignore floors. It also describes the factor composition, giving the agent insight into what drives results.

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 three sentences, with the core purpose front-loaded, the single-ticker exception stated, and the excluded instruments and alternative named. Every sentence carries substantive information; there is no redundancy or 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?

Given the tool's complexity (multi-factor scoring, optional filters, two modes), the description covers the essential usage and exclusions. A minor gap is the lack of explicit statement about the board response format (e.g., fields returned), but the output schema is absent and the description implies ranked stocks with score and ticker. Overall, it is sufficiently complete for an agent to call 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 the schema already documents every parameter. The description adds extra value by linking parameters to behavior (e.g., floors don't apply to single-ticker mode, approximation of volume) and clarifying the clamping of maxResults. It does not fully explain edge cases like how unknown market cap interacts with minDollarVolume, but it goes beyond mere restatement.

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 ranks stocks by a peer-relative 0-100 short-squeeze score, enumerating the specific factors used. It distinguishes between board ranking and single-ticker lookups, and explicitly names alternatives like GetShortInterest for excluded instruments, making its 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 (ranking stocks by squeeze risk) and when not to (excluded trusts, pointing to GetShortInterest). It also explains the two operating modes (board vs. single-ticker) and clarifies that liquidity floors only apply to the board, providing clear decision rules.

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