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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=true, and idempotentHint=false; the description reinforces the read-only contract ('reads or computes only and changes nothing') and usefully explains why it is non-idempotent — every call is charged, so repeats cost money. It adds real operational context (once-a-day refresh, $0.002/call, 25 free, failed calls free) that annotations cannot express. However, it stops short of describing response shape or ordering, so it is a solid but not exceptional add on top of the structured hints.

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?

One dense, front-loaded paragraph: what it is, what it returns, cadence, usage, example, pricing. Every sentence carries information, though the pricing/credits sentence is long and mixes commercial mechanics with functional guidance, which slightly dilutes the front-loading.

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?

There is no output schema, so the description must enumerate return values — and it does: today's value and label, 1/7/30-day change, window low/high/average, and up to 90 days of daily history. Refresh cadence, upper history bound, cost model, and safety profile are all covered, leaving no meaningful gap for a single-optional-parameter read tool.

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?

The single parameter is fully documented in the schema (1-90, default 30), so the baseline is 3. The description adds the notion of a 'window' that the low/high/average statistics are computed over and supplies a concrete invocation example (days=30), which meaningfully connects the parameter to the returned aggregates.

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 resource (Crypto Fear & Greed Index), its source (alternative.me), its scale (0 = extreme fear, 100 = extreme greed), and exactly what is returned: today's value and label, deltas at 1/7/30 days, window low/high/average, and daily history. An agent can distinguish this from price-oriented siblings at a glance.

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?

Explicitly names the use cases (market-sentiment input for a trading agent, dashboard, or daily brief) and routes elsewhere for a different need: 'for live prices use price_token.' It also warns that repeats are billable, which is a usage constraint rather than a description of behavior.

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