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

Beyond the readOnly/idempotent annotations, the description discloses the actual behavior: return contents (status, scan events, ETA), error responses (tracking_number_required, 404 tracking_not_found with status 'not_found'), normalization rules (strip spaces/hyphens, ignore case), format expectations, and the newest-first eight-event limit. No behavior contradicts the annotations.

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 description is long but dense, and every sentence contributes non-obvious information needed to call the tool correctly. It is front-loaded with the core purpose and return values, then progressively adds exclusions, parameter rules, validation, and error behavior.

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 single-parameter read tool with output schema present, the description is fully sufficient: it names what is returned, explains edge cases, defines error semantics, and clarifies when the tool should not be used. No important caller-facing behavior is omitted.

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?

Even though the schema already documents tracking_number at 100% coverage, the description adds crucial semantics: it is the only accepted key, no order id or email is accepted, values are normalized, expected carrier formats are given, and sub-6-character inputs are refused. This goes well beyond the schema's one-line description.

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 first sentence names a specific verb ('Track'), a specific resource (SMKlog shipments), and a specific lookup key (carrier tracking number). It also differentiates itself from universal trackers and from the pricing tools, so an agent can tell it apart from its siblings 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?

The description explicitly states when the tool applies ('SMKlog labels only'), when it does not ('not a universal tracker for arbitrary USPS, UPS, FedEx or DHL numbers'), and that it neither quotes nor spends quote allowance. It also points to get_checkout_status as the way to obtain the tracking number after a create_checkout_link session, giving clear routing guidance.

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