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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower and the description clears it. It adds genuinely non-obvious behavior: the data source (Legacy Futures Only), the weekly time window, the exact crowded-long/crowded-short threshold rules including hysteresis (entry at 80, exit below 75), and the COT Premium subscription requirement. Return shape and pagination are not described, but there is no output schema to compensate for.

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 core purpose is front-loaded in the first clause, and the long parenthetical is dense but every element (percentile blend, thresholds, report source) earns its place as operational detail. It is one sentence with a nested definition, which is slightly hard to parse but not padded.

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 a single optional enum parameter, rich annotations, and no output schema, the description supplies everything needed to decide whether to call it and what the filter does. The main residual gap is what the returned records look like (market names, scores, position values), which the agent must discover from the response.

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% and the side enum is already documented with its default ('both'), so the schema does the heavy lifting. The description reinforces that 'long' and 'short' refer to crowded positioning rather than raw net positions, but adds no format or edge-case detail beyond that. Baseline 3 is appropriate.

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 uses a clear verb-and-resource framing: markets where large speculators are crowded long or short this week, sourced from the Legacy Futures Only report. It goes further than the name by defining the Crowding score and its hysteresis thresholds, so an agent knows exactly what qualifies as an 'extreme'. It does not explicitly name a sibling it differs from (e.g. get_cot_index), which keeps it just short of a 5.

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 by 'this week' and the screening concept, so an agent can infer this is a weekly crowding screen rather than a lookup. There is no explicit when-to-use/when-not statement and no pointer to get_cot_index or get_latest_positions for cases where the user wants raw index values instead of extremes. The 'COT Premium only' note functions as a prerequisite rather than routing guidance.

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