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

Annotations already cover the safety profile (readOnly, non-destructive, openWorld), and the description adds genuinely non-structured facts: a live feed, that price columns are removed, a row cap of 500, and the dual auth/payment path (X-ORKID-API-Key or $0.05 USDC via x402). Pricing and auth requirements are exactly the kind of context annotations cannot express. It omits ordering/pagination behavior and freshness/latency expectations.

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 payload description, then constraints, then params, then access terms — a sensible order with no filler sentences. The telegraphic fragment style ('Live futures feed. OHLCV/settlement prices stripped') is dense but readable, though the param/pricing tail is slightly run-on.

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 does the work of enumerating returned column families, and it covers access cost and row caps. Combined with full schema coverage on the four parameters, an agent has enough to call this correctly. Missing only sort order, pagination, and how to interpret the y_* label horizons.

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 schema already documents start/end date formats, the default 100, and the 500 cap. The description's 'Params: ticker (required), start/end, limit (default 100, max 500)' largely restates the schema, adding only the required/optional grouping in one place. Baseline 3 is appropriate when the schema carries the 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?

Names the resource precisely ('Futures state-vector rows', ~130 derived columns per contract-day) and enumerates the column families returned (y_cc/y_settle/y_oc labels, roll flags, Kyle lambda, ADV share, macro context). It also carves out what it is not ('OHLCV/settlement prices stripped'), which separates it from a raw price feed. It does not explicitly contrast itself with siblings like sv_vectors or sv_fsds, so it stops 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 the content list — an agent can infer this is the labeled/feature table for futures modelling rather than raw bars. There is no explicit 'use this when / use X instead' routing against sv_vectors, sv_fsds, or sv_similar, so the agent must infer the boundary from the column inventory.

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