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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds value beyond that by defining what the returned figure actually is (subsidy plus fees, averaged per block) and by pinning the underlying REST operation, which helps an agent reason about freshness and semantics. It says nothing about aggregation granularity or caching, which keeps it from a 5.

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 short lines, front-loaded with the metric definition, followed by the docs link and the exact REST path. Every element earns its place by helping an agent map the call or verify semantics; 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?

An output schema exists, so return values need not be described, and the annotations fully cover safety and idempotency. The description supplies the metric definition and the API mapping. The only real gap is the absence of disambiguation from adjacent reward and fee siblings in a very crowded tool namespace.

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%: the single `time_period` parameter is documented with its enum values and an example in the schema itself. The description only restates 'for a time period' and adds no format or behavioral nuance (e.g. whether 'all' is unbounded cost). Baseline 3 applies when the schema does the work.

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 metric ('Get average coinbase reward (subsidy + fees) per block') plus the scoping dimension ('for a time period'), which is precise enough to identify the resource. It clarifies the composition of the reward (subsidy + fees), which is genuinely useful definitional detail. It stops short of naming how it differs from close siblings like get_reward_stats or get_block_fees.

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 only implied: an agent can infer this is the aggregate per-block reward metric over a lookback window, versus the raw per-block fee tools. There is no explicit when-to-use, when-not-to-use, or named alternative among the several reward/fee/hashrate siblings that could plausibly be chosen instead.

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