verdict

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

Annotations already cover readOnly/idempotent/openWorld/non-destructive, and the description adds genuinely non-derivable behavior: pricing via x402 (USDC on Base) or an API key, and that an unauthenticated call returns HTTP 402 with a decoded price in payment_required that is a quote, not a failure. That 402 explanation is exactly the kind of trap an agent needs disclosed; it stops just short of 5 only because rate limits/quota behavior and latency expectations are unmentioned.

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-loads the core promise in the first sentence and uses a predictable shape (what it is, example, when-to-use, when-not, behavior). It loses a point for redundancy: the asset list appears twice within the description and the 'Use when...' sentence restates the opening sentence's bias/confidence/thesis payload.

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 carries the return-value burden and does so precisely (bias, confidence, thesis, entry, invalidation, two targets, indicator readings). For a read-only single-call tool with two well-documented params, the added auth/payment semantics leave nothing an agent needs missing before calling it.

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 description coverage is 100%, so symbol's allowed values and timeframe's 15m/1h/4h/1D/1W options with default 1h are already fully documented in structured fields. The description mostly repeats that asset list and only adds a concrete request example (`/v1/verdict?symbol=BTC&timeframe=1h`), which is mild incremental value, so the baseline 3 applies.

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 and resource ('one-call trading verdict for an asset') and enumerates the exact payload: LONG/SHORT/NEUTRAL bias, 0-10 confidence, thesis, entry, invalidation, two targets, plus the underlying readings. It also names the engine inputs, so an agent can distinguish it from momentum_score (same engine, structured levels) and price/atr (raw inputs) without opening a 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?

Explicit when-to-use ('Use when you want one call that returns a LONG/SHORT/NEUTRAL bias...') and explicit when-not with named alternatives ('Not for the full structured levels (use momentum_score...) or raw inputs (use price, atr)'). Nothing about routing is left to inference.

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