Package Tracker by Spoke

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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description adds useful behavior beyond that: it returns each matching courier's ID and name, returns an empty list when nothing matches, and explicitly excludes status lookup — the empty-list contract is genuinely valuable for the caller.

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 short sentences, front-loaded with the core action, followed by the return contract and the scope exclusion. Every sentence carries distinct information with no repetition of the title or schema.

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-only lookup with an output schema, the description covers purpose, return shape, empty-result behavior, and scope boundary. Nothing an agent needs to select or invoke it correctly is missing.

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% and the schema already documents that spaces and dashes are ignored, so the parameter is fully specified structurally. The description adds only the framing that matching is driven by the code's format, which is marginal beyond the schema; baseline 3 is appropriate.

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 ('Identifies which couriers may have issued a package tracking code') and names the mechanism (code format plus courier database). It also explicitly distinguishes itself from the sibling by declaring it does not look up package status, so an agent can separate it from track_package without opening either 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 makes the use case clear (given a tracking code, find candidate couriers) and carves out the negative case by saying it does not look up status, which implicitly routes status queries to track_package. It stops short of naming the sibling explicitly or stating prerequisites, so it is clear context rather than full when/when-not guidance.

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

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

Beyond the readOnly/idempotent/openWorld annotations, the description discloses real behavior: the courier-resolution fallback chain, the candidate-list outcome when ambiguity exists, the fan-out when nothing matches, that results flag missing postalCode/country, and that every result carries a trackingUrl. That is a lot of operational detail an agent could not infer from annotations or schema.

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?

It front-loads the core action and result in the first sentence, then layers the fallback logic and the link-sharing instruction. It is dense but every sentence carries a distinct fact; a slightly tighter phrasing of the courier-resolution sentence would improve scanability.

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 four parameters, a 100%-covered schema, and an output schema already defining return values, the description covers everything an agent needs: input semantics, ambiguity handling, and the post-call obligation to share trackingUrl. No material gap remains.

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 already 100%, so the baseline is 3; the description adds value by explaining what carrierId does behaviorally (skips identification) and why postalCode and destinationCode matter (couriers that require them, surfaced when missing). It does not add format detail beyond the schema, but the conditional role of each parameter is genuinely clarified.

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 ('Gets one package's current status, courier, dates and event history') and the input that drives it ('from its tracking code'). It also implicitly separates itself from the identify_courier sibling by explaining the no-carrierId path.

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 clearly explains the flow when carrierId is absent (identify first, single match is tracked, multiple matches come back as untracked candidates, zero matches fans out across providers) and notes that some couriers require postalCode or destinationCode. It stops short of explicitly telling the agent when to call identify_courier directly instead, but the routing logic is otherwise concrete.

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