LATAM Logistics (Envia: rates, labels, tracking, cancel across MX/CO/CL/BR/GT/AR/US/CA/ES)

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

Description adds beyond annotations: notes that refund is conditional on carrier policy, returns whether label balance was returned, and requires parcel to be unscanned/undelivered. Annotations already mark destructiveHint=true, so no contradiction.

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?

Description is well-structured with action first. Some length from credential headers, but necessary for setup. Not overly verbose.

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?

Covers purpose, inputs, conditions, return value, and credentials. Lacks error handling or edge cases, but adequate for a simple tool with annotations.

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% with adequate parameter descriptions. Description restates inputs but adds little new beyond 'from create_shipment'. At baseline 3 due to high schema coverage.

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 'Cancel a shipment / label and request a carrier refund' with specific inputs (carrier code, tracking number). Distinct from siblings: create_shipment, query_tracking, quote_rates.

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?

Provides clear context: works only while parcel is unscanned/undelivered, refund timing depends on carrier. Also includes credential setup. Lacks explicit exclusion of alternatives but is otherwise thorough.

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?

Annotations indicate readOnlyHint=false, but the description adds important behavioral context: a production token buys a real label and charges your Envia balance, sandbox does not; the owner policy gate checks declared shipment value before buying; credential headers are set per-request and never stored. No contradictions with 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 a single concise paragraph that front-loads the core purpose. No wasted sentences, though the credentials section could be slightly more structured. It is efficient and clear.

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 the complexity (29 parameters, 3 required, no output schema), the description covers the tool's purpose, linkage to a sibling tool, environment differences, credential requirements, and policy gates. It does not detail error handling or response format beyond the initial sentence, but that is acceptable as the output is described succinctly.

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% (all 29 parameters described in the schema). The description adds cross-tool semantics by instructing to reuse parameters from quote_rates and provides format examples for postal codes. This linkage and the environment/credential context add value beyond the schema, justifying a score above baseline 3.

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 clearly states the action ('Buy a shipping label'), the resource ('for a specific carrier + service from quote_rates'), and the outputs ('tracking number and a printable label URL (PDF)'). It distinguishes from siblings like quote_rates (which provides rate options) and other tools like cancel_shipment or query_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?

The description provides explicit usage guidance: it tells the agent to use the same origin/destination addresses and packages as quote_rates, and to select carrier and service from a quote_rates option. It also explains environment differences (sandbox vs production) and mentions credential headers and owner policy gates. It does not explicitly state when not to use, but the context is clear.

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?

Annotations already indicate readOnlyHint=true and openWorldHint=true. The description adds rich behavioral details: returns unified status enum, plain-English hint, raw passthrough, next_steps, and error behavior for missing numbers. No contradiction with 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 somewhat lengthy due to credential details, but it is well-structured: purpose first, then output format, then notes. The front-loaded purpose aids quick understanding.

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 the simple parameter schema and no output schema, the description adequately explains the return value and credential requirements. It covers error handling and batch support, making it sufficiently complete.

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%, with each parameter described. The description adds value by clarifying the mutual exclusivity of tracking_number and tracking_numbers and confirming batch support.

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 clearly states the verb and resource: 'Track one or more shipments by their carrier tracking number(s).' It distinguishes from sibling tools (cancel_shipment, create_shipment, quote_rates) as a read-only query tool.

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 says 'Safe to call anytime' and describes batch support and error handling. It does not explicitly state when not to use, but the context of siblings and the clear purpose imply appropriate usage.

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?

Annotations declare readOnlyHint and openWorldHint; the description reinforces that the tool is read-only, buys nothing, and spends no money. It also details credential headers and environment modes (sandbox vs. production), adding transparency beyond the annotations. No contradictions.

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 a single paragraph that front-loads the main purpose but becomes somewhat lengthy with repeated credential details. It is well-structured but could be slightly more concise by avoiding redundancy (e.g., credential headers mentioned twice). Still, every sentence serves a purpose.

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 26 parameters and no output schema, the description provides a comprehensive overview: it explains what the tool returns (carrier, service, price, currency, delivery estimate, cheapest flag), covers credential headers and environment settings, and gives essential usage hints. It is complete enough for an agent to invoke correctly.

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. The description adds value by summarizing parameter groups (origin/destination addresses, packages with units) and including critical notes like Colombian DANE codes and postal format examples, which are not in the schema descriptions. However, the schema already has detailed descriptions, so the marginal gain is moderate.

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 clearly states it compares shipping rates across carriers for a route, distinguishing it from siblings like create_shipment or query_tracking. It specifies the verb 'compare' and the resource 'rates', and highlights that it's read-only and buys nothing.

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 explains when to use this tool (comparing rates), what it returns (cheapest flagged), and that it does not make purchases. It also provides credential setup instructions and hints at the difference between domestic and cross-border usage, giving clear context for use vs. alternatives.

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