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

Annotations already declare readOnly, idempotent, closed-world behavior, so the description's job is narrower. It adds real behavioral context: the geographic scope of the underlying data, the requirement to distinguish available prices from unavailable placeholders, and the prohibition on inventing prices or source categories when none exist. It says nothing about volume, rate limits, or how the tool behaves when a slug is unknown, but the core honesty constraints are disclosed.

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 sentences, and the geographic scoping constraint is front-loaded before the output-handling rules. It is dense rather than padded, though the two 'do not invent / do not substitute' prohibitions overlap slightly and could be consolidated.

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 and annotations covering safety, the description only needs to supply domain and interpretation constraints — scope, placeholder handling, and prohibitions on fabrication — and it does all of these. What remains missing is minor: it never states the failure mode for an unknown slug or whether cpt_codes narrows the explanation set.

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% and every parameter is documented there, including the slug source and the cpt_codes/limit bounds. The description adds no parameter-level meaning at all — it never mentions slug, cpt_codes, or limit. Baseline 3 is appropriate when the schema already carries the full parameter burden.

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 pairs a specific verb ('explain') with a specific resource ('price sources') and names the exact output surface it covers: source labels, counts, confidence, and caveats. It also scopes the data ('U.S. care only'), which separates it from price-returning siblings like get_entity_prices or compare_local_prices. It does not explicitly state that it retrieves records for a Loa entity slug, so an agent must infer the retrieval step.

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 a hard exclusion rule: non-U.S. care must be explained without calling this tool, and U.S. prices must never be substituted. That is a clear when-not-to-use condition. It stops short of naming a sibling alternative for the non-U.S. or plain-price-listing cases, which keeps it from a 5.

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