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

Adds real behavior beyond the readOnlyHint/openWorldHint annotations: partial-failure isolation ("one bad number never fails the rest") and a per-carrier cap of 35 that is not expressed in the schema's maxItems of 100. It doesn't cover ordering of results or what fields a per-entry "result" contains.

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 short sentences, zero filler, with the batch-size constraint front-loaded before the error-handling guarantee.

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 two-parameter read-only tool with no output schema, this covers the constraints and failure semantics an agent needs to call it correctly. Only the shape of a successful per-entry result and result ordering are left unstated, which is minor.

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?

At 50% schema coverage, the description compensates by explaining the tracking_numbers array: batch size and the 35-per-carrier constraint that the schema omits. The carrier parameter's meaning (auto-detect when omitted) is already carried by the schema, so nothing critical is missing.

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 ("Track ... numbers") plus the defining scope of the tool: batch, up to 100 numbers with 35 per carrier. This distinguishes it from the singular sibling track_package by implication, though it never names the sibling explicitly.

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 batch limits (100 total, 35 per carrier) imply this is the bulk path and track_package is the single-item path, but the description never says so. There is no explicit when-to-use/when-not or pointer to a sibling, leaving routing to inference.

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