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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds real value beyond them: the interpretive caveat that this is a descriptive statistic and not a price-direction signal, plus cost/payment context ('Paid in USDC on Base'). It stops short of stating actual pricing, rate limits, or refresh cadence.

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?

Three compact sentences, front-loaded with the metric definition and followed by scale interpretation, input modes, and cost. Each sentence carries information, though the opening sentence is dense enough that a reader has to parse it twice.

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 an output schema present, return values need no explanation, and annotations cover the safety profile. The description covers the metric, its interpretation, the input alternatives, and payment, leaving only minor gaps such as latency or freshness expectations.

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 baseline is 3, but the description goes further by explaining the either/or resolution logic between token_id and market_slug+outcome and restating the 5.0% band default. It also anchors how to read the output value (0.5 balanced, toward 1.0 bid-dominant, toward 0.0 ask-dominant), which the schema cannot convey.

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 names a precise metric ('bid-side vs ask-side order-book depth ratio, summed within depth_band_pct of each side's own best quote') and defines its scale, which alone separates it from siblings like prediction.bid_ask_spread_pct and prediction.liquidity_depth_after_haircut. An agent can identify the operation and its exact computation without opening the schema.

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?

It explains the alternative input paths clearly ('raw token_id or a market_slug (+ outcome)'), which is genuine usage guidance for call construction, and it warns the result is descriptive not predictive. But it never says when to reach for this tool over the other prediction.* siblings, so the comparative guidance is only implied.

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