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

Beyond the readOnlyHint/idempotent/destructive annotations it adds real operational context: the required Last Price credential with routing read scope, the fallback semantics when learning is not active, and the meaning of the 'learning' and 'reason' fields (not released, not turned on, strategy unsupported, still collecting data). It does not mention failure modes or timing of data refresh, which keeps it below 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?

The purpose is front-loaded correctly, but the core is one sprawling sentence where the four-way 'reason' enumeration and return-field list are chained with commas, making it hard to scan. The content largely earns its place, but the structure does not.

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 full burden of explaining return semantics and does so: it lists every reported field and explains the two status fields and their fallback behavior. Authentication scope and both parameter modes are also covered, leaving nothing essential for correct invocation unstated.

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; the description earns above that by adding the mutual-exclusivity framing the schema omits ('Instead of a policy... pass strategy') and by clarifying that strategy refers specifically to compute_price calls that enabled learned routing — meaning that is not derivable from the field alone.

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 specific verb and resource ('Read what learned routing has learned for one of your routing policies') and then enumerates the exact contents returned per function: calls seen, success rate, latency, reward rate, expected reward with interval, and current routing share. That enumeration distinguishes it clearly from neighbors like get_routing_policy (configuration) and get_learned_pricing (pricing), so an agent can identify it 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 gives concrete selection rules for both calling modes: omit policy_id to read the default policy, or pass strategy to read what was learned for compute_price calls that named that strategy with learned routing on. What it lacks is an explicit contrast against siblings such as get_routing_policy, so the agent must infer that this tool reports learned behavior rather than configuration.

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