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

With no annotations provided, the description carries the full burden of behavioral disclosure. It thoroughly explains the placeholder listing creation, idempotency (safe to re-run), retry semantics, and the manual-listing duplicate guard. It also clarifies that two auto-created listings for the same card are not duplicates. This is exceptional transparency.

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 every sentence earns its place, covering essential behavioral nuances. It is front-loaded with the main purpose before diving into edge cases. While it could be tightened, the length is justified by the complexity of the tool.

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 this complexity (order creation, listing sync, duplicate detection, retry logic), the description is remarkably complete. It explains the placeholder nature, the manual-listing check, the retry behavior, and even mentions the response indicates which existing listing to check. Nothing critical is missing for an agent to call it 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 71%, so the baseline is 3. The description adds significant meaning beyond the schema: it explains that card_name_raw must include the '(Foil)' suffix and not be stripped, and it details how items relate to listing creation. It does not explain gmail_message_id or manage_order_url, but these are likely self-explanatory metadata. The description compensates well for the coverage gap.

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 a TCGplayer order and its line items, matching cards by exact name. It distinguishes itself from read-only siblings like get_tcgplayer_orders by emphasizing the creation and listing side-effects. The verb+resource is specific and 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?

The description provides clear context: it is used when processing an order email, and it explains the downstream 'mark sold' flow for finalization. It also covers retry behavior and duplicate handling, but does not explicitly name alternative tools for similar actions. The context is sufficient for an agent to decide when to invoke it.

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?

With no annotations, the description carries the full burden of behavioral disclosure. It states the operation is diagnostic-only, which implies no data mutation, and promises full error detail for troubleshooting. It does not explicitly state that the tool makes no changes to system state or that network requests could be slow, but 'DIAGNOSTIC ONLY' covers the most important trait.

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 efficient sentence with the 'DIAGNOSTIC ONLY' warning front-loaded, followed by the action and its purpose. Every word earns its place and there is no redundant 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 zero-parameter diagnostic tool with no output schema, the description covers what it tests, where it tests to, and the nature of the result (full error detail). It provides sufficient context for an agent to decide to invoke it during connectivity troubleshooting, though it could add a note about potential network timeout behavior.

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 tool has zero parameters and 100% schema coverage, so the baseline is 4 per the rubric. The description complements the empty schema by stating exactly what connectivity will be tested, but there is no parameter information to add.

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 a specific verb ('tests') with a clear resource ('outbound HTTPS connectivity'), and specifies two targets: a generic endpoint and the configured Supabase URL. It is immediately distinguishable from the sibling tools, which are all business-data operations (inventories, prices, orders), not diagnostics.

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 leading 'DIAGNOSTIC ONLY' label clearly signals that this tool is for troubleshooting, not routine use, providing an implicit exclusion. It names its purpose—testing connectivity to the Supabase URL—but does not explicitly name alternative diagnostic tools or state when not to use it. Still, the diagnostic context is unmistakable.

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 are provided, so the description carries the behavioral burden. It usefully defines the PnL formula, but it does not disclose how results are aggregated or ordered, what the default behavior is when box_id is omitted, or what the return structure looks like.

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 with no filler. The core purpose is front-loaded, followed by concrete example questions that help an agent select the tool quickly.

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?

The description is adequate for tool selection but not fully sufficient for invocation: there is no output schema, no annotations, limit semantics are unexplained, and the relationship to the similar sibling get_global_pnl is not addressed.

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 schema covers box_id with a description, but limit has no schema description. The tool description adds 'per box' context and implies optional filtering, but it never explains the limit parameter's meaning, default, or effect, leaving one of two parameters effectively undocumented.

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 a specific verb and resource: 'Get profit & loss per box' and explains the calculation basis ('purchase price vs. realized/unrealized value of pulled cards'). This distinguishes it from sibling tools like get_global_pnl, which would address portfolio-level P&L.

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 use cases: 'was Box X worth it' or 'how is Gothic performing overall' questions. It gives clear context for when to use the tool, though it does not explicitly contrast it with alternatives like get_global_pnl or state when not to use it.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It implies a read-only operation by using 'Get', but does not explicitly state that it has no side effects or that it returns a list of listing objects. It also does not mention pagination, sorting, or any rate limits. For a simple get operation, this is acceptable but not thorough; a 3 reflects the absence of any explicit behavioral caveats.

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, front-loaded sentence that states the core action and includes two illustrative examples. There is no redundant wording or unnecessary detail. It is concise and immediately informative, earning full marks for structure.

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?

The tool has only two parameters and no output schema, so the description should clarify what the response contains. It states that it returns 'listings' but does not specify fields (e.g., listing ID, title, price) or the shape of the response. It also does not mention how 'limit' affects the output. For a simple list tool, this is a moderate gap; an agent might need to infer the response structure. Given the low complexity, a 3 is appropriate.

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 schema already describes the 'status' parameter with an enum and a short description, and the tool description reinforces its meaning with 'active or sold'. The 'limit' parameter has no schema description and is not mentioned in the tool description, but its purpose (limiting the number of results) is self-evident. Since schema coverage is 50%, the description partially compensates for status but not for limit, which is a minor gap. Overall, the description adds some value beyond the schema but does not fully compensate for the missing limit explanation.

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 'Get' and the resource 'eBay listings', and further specifies the two possible statuses (active/sold) with concrete example questions. This distinguishes it from sibling tools like get_inventory_summary or get_latest_prices, which focus on different data. The purpose is unambiguous and immediately actionable.

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 clear usage context through example questions ('what do I have listed right now' or 'what has sold recently'), which effectively tells an agent when to invoke this tool. It does not explicitly name alternatives or exclusions, but the examples and the tool's focus on listings make the appropriate scenario obvious. A small deduction for not explicitly stating when not to use it, but the guidance is strong.

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 are provided, so the description carries the full burden of behavioral disclosure. It clearly explains what the result represents (total spend vs. realized + unrealized value), but it does not explicitly state read-only behavior, data freshness, or any side effects. The 'Get' verb implies non-destructive behavior, but that is not made explicit.

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 short sentences with no filler. The first sentence states the core function and formula, and the second sentence gives a direct usage example. Every sentence earns its place.

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 zero-parameter tool with no annotations and no output schema, the description is largely complete: it states what is computed, the scope, and when to use it. It does not explicitly describe the return format, but the named components ('total spend', 'realized + unrealized value') give sufficient context for an agent to interpret the result.

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 tool has zero parameters, so there is no parameter semantics to document. Per the calibration baseline, 0 parameters warrants a 4; the description appropriately focuses on the tool's purpose rather than on nonexistent inputs.

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 a specific verb ('Get') and a clear resource ('overall business P&L across all boxes/listings'). It also specifies the computation basis ('total spend vs. total realized + unrealized value'), which distinguishes it from more granular siblings like get_box_pnl.

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 gives an explicit use case: 'Use for "how is the business doing overall" questions.' This provides clear context for when to invoke the tool, though it does not explicitly name alternatives or state when not to use it.

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 are provided, so the description carries the full burden of behavioral disclosure. It only says 'Get' which implies a read operation, but does not explicitly state it is read-only, nor does it mention any side effects, caching, or data freshness. For a tool with zero annotation coverage, this is a significant gap.

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 with no filler. The first sentence states the exact functionality and outputs; the second provides concrete usage examples. It is front-loaded and every word earns its place.

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?

There is no output schema, so the description should explain the return format. It mentions the data types (cards on hand, quantities, prices) but not the structure (e.g., single summary object, array, pagination). The limit parameter hints at possible pagination but it's not described. Given the absence of annotations and output schema, the description is adequate but not 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 description coverage is 100%: both parameters (limit, name_contains) have descriptions in the schema. The tool description adds no parameter-specific information, but the schema already documents them adequately. The baseline of 3 applies because the description doesn't compensate or add extra context, but the schema covers the essentials.

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 retrieves the current inventory dashboard, listing specific data (cards on hand, quantities owned/listed, latest market prices). It provides example questions ('what do I have in stock', 'what am I sitting on that I should list') that make the purpose unmistakable and distinguish it from siblings like get_latest_prices (price-specific) or get_box_pnl (profit/loss).

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 says 'Use for questions like...' giving direct when-to-use guidance. It doesn't mention when not to use it or name alternatives, but the provided examples are sufficient to route an agent correctly for inventory summary queries.

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?

With no annotations, the description must carry behavioral disclosure. It correctly conveys a read operation and the returned data type (market prices plus cost basis), which makes side effects unlikely. However, it omits response shape, pagination/limit behavior, and any freshness or authorization caveats, so transparency is adequate but incomplete.

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 filler: the first states function and filtering capability, the second provides concrete use cases. The key action is front-loaded and every clause earns its place.

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 optional-parameter getter, the description covers purpose and common use cases. Yet because there is no output schema, it should clarify return format and limit semantics; those gaps prevent full completeness for an agent selecting and invoking the 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 coverage is only 50%; 'limit' has no schema description. The tool description rephrases name_contains as 'optionally filtered by name' but adds no detail about the meaning or effect of limit (e.g., maximum result count). Thus the description does not meaningfully compensate for the undocumented parameter.

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 opens with a specific verb and resource: 'Get latest TCGplayer market prices and cost basis for cards.' It also notes the optional name filter. This clearly separates it from siblings like get_price_alerts or get_global_pnl, which concern alerts or P&L rather than current market prices.

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 second sentence explicitly maps the tool to user intents: 'what is X worth' and 'what did I pay vs. what is it worth now.' It gives clear contexts for use but does not name sibling tools or state when not to use it, so it stops short of full exclusion 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the exact matching logic, the duplicate-sale guard, the false-positive risk from price refreshes, and the edge case where auto-created listings from other orders do not count as coverage. This is unusually transparent about how the tool computes results.

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 front-loaded with the core purpose and the most important caveat about false reads, followed by precise edge-case details that genuinely matter. It is long and dense, but no sentence is filler; a slightly tighter structure could make it easier to scan.

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 complex tool with no output schema and no annotations, the description provides the core output semantics ('listing every line item on the order') and covers all important matching/coverage rules. It stops short of explicitly describing the full response envelope, such as order fields or counts, but an agent still has enough to invoke it 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%, so the parameters are already documented. The description adds meaningful usage context for `since` by explaining when to set it versus omit it, and the `limit` parameter is already well explained by the schema. This is a clear improvement over the baseline, though it does not add much beyond the schema for `limit`.

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: 'Find TCGplayer orders whose listing/inventory sync never completed.' It also distinguishes itself from naive alternatives by explaining that it is not an inference from quantity_listed or updated_at, which makes the purpose and scope unmistakable even among sibling order tools.

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 gives concrete guidance on when to invoke it: with `since` set to the start of an order-capture run to catch a bad sync quickly, or with no `since` for a full backlog sweep. It does not explicitly name an alternative or state when-not-to-use this tool, but the context is clear enough for an agent to select it correctly.

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 are present, so the description carries the full burden. It discloses that the tool returns current, non-dismissed alerts and optionally includes listing and stale data, which implies a read-only operation. It does not mention permissions, rate limits, or return format, but for a simple getter the information is adequate; it adds value beyond the schema by clarifying the 'non-dismissed' state and the optional inclusions.

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, with the primary function stated first and the usage examples following. There is no fluff; every word contributes to understanding what the tool does and when to use it. It is efficiently structured and 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 has no output schema, the description does not explain the response structure, which could be important for an agent to parse the returned data. It implies the output includes sections for price alerts, listing alerts, and stale listings, but does not detail fields or pagination. For a tool of moderate complexity, the description is somewhat incomplete without return format details.

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 each parameter already has a clear description. The tool description adds minimal extra meaning—only the phrase 'optional context' for the two boolean parameters, which mirrors the schema. It does not provide syntax, types, or additional semantics beyond what the schema already gives.

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 retrieves current, non-dismissed price alerts with optional context for eBay listing and stale listings. It provides concrete example questions the tool answers, making its purpose unambiguous and distinct from siblings like get_ebay_listings or get_latest_prices by focusing on the alert aggregation and non-dismissed filter.

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 explicitly gives usage guidance via example questions ('what should I look at today' or 'anything moving I should react to'), which tells an agent when to invoke this tool. However, it does not explicitly mention when not to use it or name alternative tools, leaving the comparison to siblings implicit.

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 are provided, so the description carries the full burden of behavioral disclosure. The verb 'Get' implies a read operation, but the description doesn't mention authentication, rate limits, whether it modifies data, how results are ordered, or what happens when both status and order_number are provided. The only extra bit is 'and their line items', which is a return-value detail, not a behavioral trait.

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 with no wasted words. The core function and filtering options are front-loaded in the first sentence, and the second sentence provides practical examples. Every sentence earns its place.

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?

The tool has no output schema and no annotations, so the description must carry more weight. It does state that orders and their line items are returned, which is a helpful high-level overview. However, it doesn't mention default limit behavior, pagination, or any caveats about the data returned, making it adequate but not 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 description coverage is 67%, above the 50% threshold, so baseline is 3. The description adds some meaning by relating parameters to use cases ('what did order X contain' maps to order_number, 'what orders do I need to ship' maps to status), but it does not add anything about the limit parameter or clarify interactions between filters.

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 a specific verb and resource: 'Get TCGplayer orders and their line items', which clearly distinguishes this tool from siblings like get_inventory_summary or get_orders_missing_listings. It also provides concrete example questions that anchor the tool's purpose.

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 gives explicit context by mentioning questions like 'what TCGplayer orders do I need to ship' and 'what did order X contain', which tells the agent when to use this tool. It does not explicitly exclude alternatives or mention when not to use it, 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals that it calls an export API directly, saves PDFs locally, returns paths, requires a session cookie, and that the cookie expires (with 401/403 as a signal). It also explains the auto-format splitting behavior for mixed batches, making side effects and prerequisites explicit.

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, with every sentence earning its place. It is front-loaded with the core purpose, then details format logic, cookie requirements, and error handling. The structure is logical and efficient, avoiding redundancy while covering all necessary aspects.

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 complexity (format selection, multiple orders, cookie dependency), the description is remarkably complete. It explains the return value (path), the auto-format rules, the cookie acquisition and refresh, and the error indication. There is no output schema, so the description adequately covers what an agent needs to call it 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%, but the description adds significant meaning beyond the schema: it explains the auto-selection of format based on order_total, the meaning of each format enum value, and the behavior of mixed batches. This goes well beyond the schema's basic descriptions, providing the agent with decision-making 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 description clearly states the specific verb (generate), resource (packing-slip PDFs), and scope (for one or more order numbers). It distinguishes itself from sibling tools by being the only one that produces packing slips, and it explicitly mentions bypassing the Seller Portal button, which further clarifies its unique role.

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 explains exactly when to use this tool (to generate packing slips) and provides the alternative (the Packing Slip button) that it replaces. It also details the auto-format selection logic and the cookie prerequisite, giving clear operational context without ambiguity.

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