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

Annotations already declare readOnlyHint=true and openWorldHint=true, but the description adds materially useful context: probes are limited to three endpoints, they are performed unpaid (no charge incurred), and ranking is by observed live response time rather than historical or outcome-based metrics. This clarifies the semantics of the ranking and the financial safety of the call beyond what annotations convey.

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?

Two tightly written sentences: the positive capability first, then a single scoping/exclusion sentence. No filler, no repetition of the title, and the key constraint ('up to three', 'unpaid') is front-loaded.

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?

For a read-only probe tool with a one-parameter schema and no output schema, the definition covers what it does, the scope limit, and the measurement basis. It leaves minor gaps around partial-failure behavior and what a 'valid live payment challenge' entry contains, but nothing critical for correct invocation.

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 0% for the single 'ids' parameter, so the description must carry meaning: it establishes that the ids are catalog endpoints and that at most three are probed, matching the schema's maxItems of 3. It does not clarify id syntax, uniqueness, or what happens if an id is invalid, so it only partially compensates for the coverage gap.

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 gives a specific verb and resource ('Probe up to three catalog endpoints') plus the operation's output ('rank valid live payment challenges by observed response time'). It is clearly a live-probe/ranking tool rather than a search or purchase tool, though it never names a sibling to distinguish itself from search_catalog or start_purchase.

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?

The 'unpaid' framing implies it is a pre-purchase validation step, and the negative clause ('Does not measure historical uptime, paid success or outcome quality') sets boundaries on what the results mean. However, there is no explicit statement of when to choose this over search_catalog or start_purchase, so the guidance is implied rather than stated.

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