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

Annotations already declare the operation read-only, idempotent, and non-destructive. The description adds useful behavioral details beyond the annotations: result ordering, response contents, and explicit error behavior for an unknown email.

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 tight sentences convey the result set, ordering, contents, and failure mode with no redundancy. All sentences earn their 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 read-only lookup with an output schema and full parameter documentation, the description covers the important non-obvious aspects: ordering, response fields, and the no-match error. Nothing needed for correct invocation 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%, with customer_email and limit fully described in the schema. The description does not add parameter-specific meaning beyond the schema, but it reinforces the email as the lookup key and implies the limit controls the number of recent orders.

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 identifies the tool's output: a customer's most recent orders, ordered newest first, with status, line items, and total. It is distinct from sibling tools like search_products or sales_summary, which address different 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?

The intended use case is evident: retrieve order history for a specific customer by email. It does not name alternative tools or exclusion conditions, but the context is unambiguous and the sibling tools are clearly unrelated.

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, idempotentHint, and destructiveHint, covering the safety profile. The description adds valuable behavioral context: the sorting order (lowest stock first), the time window (last 30 days), and the included metrics (units sold and revenue). This goes beyond the annotations and helps the agent understand what the result set contains.

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, well-structured sentence. It front-loads the primary action (products running low on stock) and appends the key details (lowest first, units sold, revenue, last 30 days). There is zero redundancy or unnecessary wording.

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 is simple with one optional parameter and an output schema present. The description covers the core behavior (which products are returned, sorting, metrics, time window). It does not mention pagination or response limits, but given the read-only nature and the presence of an output schema, this is not a significant gap. The description is complete enough for correct invocation.

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 fully documents the single 'threshold' parameter with description, default, min, and max (schema coverage 100%). The description does not add any additional meaning about the parameter, so it relies entirely on the schema. Baseline 3 is appropriate given the 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?

The description clearly states the tool's purpose: it returns products running low on stock, sorted by lowest stock first, along with units sold and revenue over the last 30 days. This distinguishes it from siblings like top_products (which focuses on bestsellers) and sales_summary (aggregate sales). The verb+resource is specific and 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 implies a clear use case ('to decide what to restock') but does not explicitly mention when not to use this tool or compare it with alternatives like top_products or sales_summary. The context is clear enough for an agent to infer, but explicit exclusions are missing.

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 mark the tool read-only, idempotent, and non-destructive, so the description does not need to re-state safety. It adds valuable behavior beyond the schema: canceled orders are excluded, empty ranges return zero totals, and week grouping starts on Monday. These are meaningful edge-case disclosures.

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?

A single, information-dense sentence front-loads the core metrics, then covers date range, grouping options, exclusions, and empty-range behavior. Every clause earns its place; there is no filler or repetition of schema details.

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 read-only annotations, a fully descriptive input schema, and an existing output schema, the definition covers the essential behavioral nuances: aggregation scope, grouping, cancellation exclusion, and zero-total behavior. Nothing an agent needs to decide whether and how to call this tool 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%, so the baseline is 3, but the description adds semantic value by specifying that 'week' grouping starts on Monday and that the result includes both a total and a per-period breakdown. This goes beyond the schema's terse 'Period size for the breakdown'.

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 identifies the tool's output: revenue, order count, and AOV for a date range, with optional daily/weekly/monthly breakdowns. It does not use an explicit verb like 'returns' and does not name a sibling alternative, but the metrics and date scope make the purpose unmistakable and distinguish it from order/product/inventory siblings.

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 when to use the tool—when aggregate sales metrics over a date range are needed—but it does not explicitly state when not to use it or point to alternatives such as get_customer_orders for per-customer detail. The grouping and exclusion behavior help, but there is no direct routing 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?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering the safety profile. The description adds valuable behavioral context: it explains that the search is semantic (not keyword-based) and describes the output format, including a cosine similarity score with a threshold interpretation (~0.8 = strong match). This goes beyond the annotations and helps the agent interpret 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 two concise sentences that front-load the core purpose and immediately explain the distinguishing feature (semantic matching). It also includes the key output detail (similarity score and threshold) without any fluff. Every sentence earns its place, making it an efficient and well-structured definition.

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 complete for an agent to call the tool correctly: it explains the semantic matching behavior, the return fields (price, stock, similarity score), and the threshold for a strong match. An output schema exists, so the return structure is further documented. The only minor omission is a mention of result ordering or pagination, but the limit parameter is described in the schema, so this is not a critical gap.

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 provides full descriptions for all three parameters (query, limit, category) with a 100% coverage, so the baseline is 3. The description does not add any parameter-specific details beyond what the schema already includes; it mentions the query concept implicitly but does not clarify limit or category behavior. Thus it adds no extra parameter semantics.

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 (semantic search) and resource (products), and highlights the distinctive feature that it matches meaning even without shared keywords. This distinguishes it from the sibling tools, which are focused on orders, sales, top products, and low stock alerts, all non-search utilities.

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 for semantic product discovery but does not explicitly state when to prefer this tool over alternatives or when not to use it. It mentions 'even without shared keywords' which suggests a fuzzy-match use case, but no explicit guidance or exclusions are given. Since the siblings are clearly different (reporting/analytics vs. search), the lack of explicit direction is a minor gap.

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, idempotentHint, and non-destructive behavior, so the safety profile is established. The description adds valuable behavioral context by stating that cancelled orders are excluded and that a salesless range returns an empty list, which helps set agent expectations.

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, front-loading the core purpose and adding an edge-case behavior second. Every word contributes to understanding the tool's function.

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?

Combined with the complete input schema, an output schema, and annotations, the description covers the remaining operational nuances: date-bounded ranking, exclusion of cancelled orders, and empty-list behavior. Nothing essential for correct invocation 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?

Input schema coverage is 100%, with thorough descriptions for start_date, end_date, limit, and the by enum. The description does not need to repeat those details; it adds only the high-level ranking concept already implied by 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 opens with 'Best-selling products between two dates, ranked by revenue or by units sold,' clearly specifying the verb, resource, and ranking dimension. This makes the tool's purpose distinct from siblings like get_customer_orders or sales_summary without ambiguity.

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 for when to use the tool: retrieving top products in a date range, optionally ranked by revenue or quantity. It does not explicitly name sibling alternatives or when-not-to-use conditions, but the use case is evident enough for an agent to select it appropriately.

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