easypost

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

Beyond annotations (destructiveHint=true), description details financial charge, irreversibility, and refund option, adding critical behavioral context.

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?

Four sentences, front-loaded with action, warning, and usage. No redundancy, includes API endpoint for reference.

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?

Complete for a transactional purchase tool: explains effect, prerequisites, and reversal path. No output schema but impact is clear.

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 good param descriptions. Description adds context for rate_id (from create_shipment/get_shipment), slightly improving over schema alone.

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 'PURCHASE a shipping label' and distinguishes from siblings like easypost_create_shipment and easypost_refund_shipment.

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?

Explicitly tells when to use: pick a rate_id from previous calls, warns about charges, and suggests refund alternative for reversal.

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 non-destructive and non-read-only. The description adds value by specifying that the tool does not charge or purchase, and only rates. It covers the behavioral boundary clearly.

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 concise sentences, front-loaded with the main action, and no redundant or wasteful content. 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?

For a tool with 5 parameters and nested objects, the description covers the core behavior (rates returned), which is sufficient given no output schema. Minor omission: does not mention that a shipment object is created and stored.

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%, so parameters are well-documented in the schema. The description does not add additional meaning beyond what the schema provides, meeting the baseline for high 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?

The description clearly states the action (create shipment), the key nuance (only rates, does not buy), and distinguishes from the sibling tool easypost_buy_shipment. It uses specific verbs and resources.

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?

Explicitly states when to use (for getting rates without purchasing) and when not to (not for buying a label), and points to the correct sibling tool for the next step.

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 and destructiveHint=false, so the description correctly implies a creation action. It adds 'No charge' and 'Returns the tracker with current status', which are useful behavioral details beyond the annotations. However, it doesn't describe side effects like duplicate handling.

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 two sentences, front-loading the action and result with no unnecessary words. Every part serves a purpose: what it does, what it returns, cost, and API reference.

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 tool's simplicity (2 params, no output schema, annotations covering safety), the description covers all essential aspects: purpose, result, cost, and API endpoint. It is fully complete for the agent to select and invoke this tool.

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 description coverage is 100%, so the schema already effectively documents both parameters. The description does not add any new parameter semantics beyond restating 'carrier tracking code'. Baseline 3 is appropriate as the description provides no added value for parameters.

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 ('Start tracking a package'), the resource ('by its carrier tracking code'), and the outcome ('Returns the tracker with current status'). It also mentions the API endpoint, providing specificity. This distinguishes it from siblings like easypost_get_tracker, which retrieves existing trackers.

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 includes 'No charge', which implies a cost benefit, but does not explicitly state when to use this tool versus alternatives like easypost_get_tracker or easypost_create_shipment. It provides context but lacks exclusions or direct comparisons to siblings.

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 declare readOnlyHint=true, indicating a safe read operation. The description adds value by stating the tool returns verification details and specifying the HTTP method (GET). No behavioral contradictions or missing critical traits for this simple retrieval.

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 extremely concise with two sentences that front-load the purpose. Every sentence adds meaningful information without any waste.

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 tool's simplicity (one parameter, no complex output), the description is mostly complete. It could be enhanced by briefly noting the response structure, but as a retrieval endpoint with annotations handling safety, it adequately serves its purpose.

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?

The input schema already provides a clear description for the only parameter 'id'. The tool description does not add additional parameter-level meaning beyond the schema, which has 100% coverage. Baseline score of 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?

The description uses the strong verb 'Retrieve' and specifies the resource 'a single address by id', clearly distinguishing it from siblings like easypost_list_addresses and easypost_verify_address. It also mentions inclusion of verification details and the API endpoint.

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 implies use when you need a specific address by ID, but does not explicitly state when to use this tool versus alternatives (e.g., listing or verifying addresses). No exclusion criteria or prerequisite information is provided.

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 provide readOnlyHint=true. Description adds that the tool returns rates, tracking_code, and postage_label conditionally (if purchased), and mentions the API endpoint. Sufficient behavioral context beyond 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?

Single concise sentence plus API endpoint. No wasted words, perfectly front-loaded.

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 tool's simplicity (one parameter, read-only, no output schema), the description fully covers what the tool does and returns. No gaps identified.

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?

Parameter 'id' is well explained in the schema ('Shipment id, e.g. shp_...'). Description adds no extra meaning beyond stating 'by id'. Schema coverage is 100%, so baseline applies.

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 'Retrieve a single shipment by id' and lists included fields (rates, tracking_code, postage_label). Distinguishes from sibling tools that create, buy, list, or track shipments.

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?

Implied usage when you have a shipment id and need detailed information, but no explicit guidance on when to use this over siblings like get_tracker or get_address. Lacks when-not-to-use statements.

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 declare readOnlyHint=true, so the description's 'retrieve' is consistent. Description adds that it includes status and history, which is useful but not extensive. 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?

Two sentences, efficient and front-loaded. First sentence states purpose and output, second provides API endpoint. No wasted words.

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 single parameter, full schema coverage, and readOnly annotation, the description is sufficient for an agent to use the tool. It explains what the tool returns. Lacks mention of error handling or limitations, but acceptable.

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 one required param 'id'. Description mentions 'by id' and the API path, but adds no new semantic detail beyond the 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?

The description clearly states the verb 'retrieve', the resource 'single tracker by id', and includes what data is returned (current status, tracking_details history). Differentiates from siblings like list_trackers or create_tracker.

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 implies use when you have a tracker id and need details, but does not explicitly state when not to use or mention alternatives. Context is clear enough for a simple retrieval tool.

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 declare readOnlyHint=true. The description adds the API method (GET) and pagination behavior, but does not disclose additional traits like default ordering, response limits, or any side effects. 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?

Two sentences with zero wasted words. Front-loaded with purpose, then pagination detail and API reference. Highly efficient.

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 paginated list tool with clear parameters and read-only annotations, the description is adequate. However, it could mention default sort order or response structure to be fully 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 clear descriptions for all three parameters (after_id, before_id, page_size). The description adds no further meaning beyond the schema, earning the baseline score.

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 'List saved addresses on the account, with pagination' and specifies the API endpoint, distinguishing it from sibling tools like easypost_get_address (single address) and list operations for other resources.

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 guidance is provided on when to use this tool versus alternatives like easypost_list_shipments or easypost_list_trackers. The description lacks context for choosing based on use case.

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 declare readOnlyHint=true, indicating a safe read operation. The description adds behavioral nuances: results are 'most recent first,' pagination is supported, and filters are optional. It also mentions the API endpoint, which provides implementation context. 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?

Two sentences: first states purpose and key behaviors, second provides the API reference. Every word is functional, no redundancy. Information is front-loaded and immediately useful.

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 list tool with no output schema, the description covers the essential: what it lists, ordering, pagination, and filters. It doesn't describe the return format or pagination details (e.g., cursor tokens), but that is optional given the schema covers filter parameters. The context is sufficient for an AI agent to decide when to use it.

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?

All 6 parameters have descriptions in the schema (100% coverage), so the baseline is 3. The description adds no additional parameter-level meaning beyond what the schema provides. It only mentions 'optional filters' generically, which the schema already details.

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 'List shipments on the account, most recent first, with pagination and optional filters.' It specifies the resource (shipments), ordering (most recent first), and key features (pagination, filters). The addition of the API endpoint provides technical context. This distinguishes it from sibling list tools (addresses, trackers) and other operations.

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 implies usage context: when you need to fetch a list of shipments with optional filters and pagination. While it doesn't explicitly state when not to use or mention alternatives (e.g., get_shipment for a single shipment), the sibling tool names and the description's specificity make the intended use case 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 declare readOnlyHint=true, so the description's value is limited. It adds 'API: GET /trackers' but no additional behavioral context such as pagination behavior, data freshness, or permission requirements.

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, front-loaded with the key action and resource. Every word carries weight; no extraneous content.

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 list operation, the description is largely complete. The page_size parameter is covered. However, no output schema exists and the description does not explain return format or pagination behavior, which would be helpful.

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 parameters are described in the schema. The description's mention of 'filtered by tracking_code or carrier' summarizes the filtering but does not add meaning beyond the 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?

The description clearly states the action (List), the resource (package trackers), and optional filters (tracking_code or carrier). It distinguishes from siblings like easypost_get_tracker and easypost_create_tracker.

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 implies usage via optional filters but does not explicitly state when to use this tool versus alternatives (e.g., get_tracker for single lookups). No exclusions or prerequisites are mentioned.

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 destructive hint, and description adds context that approval depends on carrier and label age, enhancing transparency beyond 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?

Two concise and front-loaded sentences with no redundancy, effectively communicating action and warning.

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, the description covers purpose, warning, and API endpoint adequately, though could mention refund uncertainty.

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% for the single 'id' parameter, and description adds no extra semantic meaning beyond what's in the 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?

The description clearly states it requests a refund/void of a purchased shipping label, with specific verb and resource. It distinguishes from siblings like create or buy.

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 a warning about carrier and label age dependency, which implies when it might fail, but lacks explicit guidance on when to use this tool vs alternatives like cancelling or creating a new label.

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 non-destructive; description adds no-charge info but lacks details on side effects like storage or modification of the address.

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 concise sentences front-load purpose and key details (no charge, API endpoint) without waste.

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?

Without output schema, description is vague on return format; adequate for a verification tool but leaves gaps for optional parameters.

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 only 40%; description only mentions the envelope structure and verify flag, not compensating for undocumented parameters.

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 tool creates and verifies an address, returns deliverability and normalized fields, and distinguishes it from siblings like get_address and create_shipment.

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 implies use for address verification and notes no charge, but does not explicitly contrast with sibling tools for when to use alternatives.

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