Multi-Carrier Tracking

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

No annotations provided, so description carries full burden. It transparently states it returns a primary guess and candidates for ambiguous numbers, and that it does not fetch status. Could mention error handling or unknown carriers but sufficient.

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 sentences with no wasted words. Front-loaded with the primary action. Very concise and to the point.

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 simple tool with one parameter and no output schema or annotations, the description is quite complete. It covers input, output structure, and behavior. Minor gaps like error handling could be addressed but not critical.

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 has 0% coverage (no description for tracking_number parameter). Description compensates by explaining the parameter's purpose (tracking number for carrier detection). For a simple string parameter, this is adequate.

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?

Description clearly identifies the verb ('Identify'), resource ('carrier for a tracking number'), and scope ('without actually fetching status'). It distinguishes itself from siblings like track_package by stating it does not fetch status.

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?

Description implies when to use this tool (before tracking to identify carrier) and mentions it returns candidates for ambiguous numbers. However, it does not explicitly state when not to use or compare directly to siblings, but the context is clear enough.

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?

No annotations provided; description does not disclose behavioral aspects such as read-only nature, rate limits, or definition of 'supported'. The agent has no indication if this is a safe read operation.

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?

One sentence, no filler, front-loaded with purpose. Every word contributes.

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?

Given zero parameters and no output schema, the description is adequate but could mention output format or that it returns a list of carrier-country pairs. It meets minimum requirements but lacks depth.

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?

No parameters exist, so the description does not need to add parameter info. Baseline 4 applies as per instructions.

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?

Clearly states the action (list) and the resource (supported carriers and their countries). Distinguishes from sibling tools (detect_carrier, track_multiple, track_package) which are for detection and tracking.

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?

No explicit guidance on when to use or alternatives. However, the tool is simple and self-explanatory; lacking exclusion criteria reduces score.

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?

No annotations provided, so description carries full burden. It discloses auto-detection of carriers, same-order results, and that slower entries are not retried within the batch. This covers key behavioral traits for a batch tool.

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, clear sentences with no redundancy. Front-loaded with 'Batch tracking' and immediately provides key limits and behaviors.

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 simple single-parameter tool without output schema, description is sufficiently complete. It covers input limits, processing behavior, and output ordering. Minor omission: no mention of error handling or empty list case.

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?

With 0% schema description coverage, description adds meaning: batch limit of 25, auto-detection, ordering. Schema only defines type and maxItems; description enriches with behavioral context.

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 tool name and description clearly indicate batch tracking. It distinguishes from sibling tools like track_package (single) and detect_carrier (carrier detection only). The verb 'batch tracking' plus specifics (up to 25 numbers, auto-detect carrier, same order) make purpose unambiguous.

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?

Description implies use for batch tracking but doesn't explicitly state when to choose this over track_package or detect_carrier. It mentions limits and behavior but lacks explicit 'use this when' 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?

No annotations provided, so description must cover behavior. It discloses auto-detection of carrier and return format (structured events with timestamp, status, location). Could mention rate limits or error handling, but adequate for this tool.

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 sentences, no fluff. Front-loaded with main purpose. Every clause adds information.

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 simple tracking tool, description covers all needed points: input (tracking number, optional carrier), behavior (auto-detection), output (events with timestamp, status, location). No output schema but description compensates.

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%, baseline 3. Description adds value: 'spaces/dashes ignored' for tracking_number, and 'pass carrier explicitly if detection is ambiguous'. These go beyond schema.

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?

Description clearly states verb (get) and resource (status and event history for a single package). Distinguishes from siblings by specifying 'single package' vs. multiple tracking, and mentions auto-detection which differentiates from detect_carrier and list_carriers.

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?

Tells when to explicitly pass carrier (if detection ambiguous). Implicitly guides to use track_package for single package vs. track_multiple. Does not explicitly state when NOT to use, but context is sufficient.

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