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

Annotations already cover read-only/idempotent/open-world safety, so the description's added value is the data shape: a fixed 6-hour window with 36 samples, base fee per block on EVM, TPS samples on Solana. That is real behavioral context beyond the annotations, though it says nothing about pagination, staleness or latency.

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 capability and window, then scope, then the use-case question, then exclusions. Every sentence earns its place with no filler.

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 not be explained; the description covers window, sampling density, per-chain semantics and sibling differentiation. Nothing needed to call it correctly is missing.

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 enum description already enumerates chains, so the baseline is 3. The description earns a bump by explaining what the chain parameter actually yields per family (base fee per block for EVM, TPS samples for Solana), which the schema does not 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?

States a specific verb and resource (get gas fee trend) plus scope (6-hour window, 36 sampled points) and chain-specific semantics for EVM vs Solana. An agent can immediately distinguish this from gas.tracker, gas.predict and gas.optimize.

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 natural-language question it answers ('how have fees behaved recently?') and enumerates the three sibling tools it is NOT, with the role each plays (current quote, forecast, submission recommendation). Routing is unambiguous.

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