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

While annotations handle safety hints (readOnlyHint: true), the description significantly exceeds expectations by detailing the entire return payload, including contact details, credit limit, specific amount types (invoiced, paid, open, overdue), and detailed counts.

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 moderately detailed, but every sentence contributes necessary information—purpose, examples, and return structure—making the overall structure highly effective.

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 definition is highly complete. By listing every single data point returned (from contact details to overdue invoice details), it gives the agent maximum context regarding the operation's output.

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?

Since schema coverage is 100%, the baseline score of 3 is met. The description merely reinforces the accepted formats for the customer input (code or name) which are already 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 purpose is stated immediately and clearly: 'Get a customer's account balance (accounts receivable).' This is specific and easy for an agent to identify.

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, real-world examples of how and when to use the tool, such as checking 'What is Oakhurst's open balance?' or determining if a customer is over credit limits.

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 read-only, idempotent, non-destructive behavior, so the safety profile is covered. The description adds a real behavioral trait not in the annotations: partial periods produce a like-for-like comparison, which affects how results should be interpreted. It does not mention data freshness or latency, which keeps it below 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short paragraphs: purpose, then intent examples, then a concrete invocation with the partial-period caveat. Every sentence carries information and the most decision-relevant content is 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?

An output schema exists, so return values need no explanation, and the description covers the metric list restriction, date-range framing, comparison behavior, and concrete intents. What remains thin is guidance on choosing between the ranking metrics and the per-entity siblings such as list_overdue_orders.

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%, including detailed enum value meanings for metric and the comparison-window rules for compare_previous, so the baseline is 3. The description repeats those same fields in its example call without adding syntax or constraints beyond the schema; only 'fixed list of metrics' lightly reinforces the enum.

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?

States a specific verb and resource ('Calculate a business KPI for a date range') and scopes it to 'a fixed list of metrics', which signals the enum. It implicitly separates itself from per-record siblings like get_order_status or get_customer_balance by framing this as aggregate reporting, but never names a sibling, so differentiation is by inference.

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 three example questions ('How did revenue this quarter compare to last quarter?', 'Top 5 products last month', 'How much is overdue?') effectively map natural-language intents onto specific metrics, which is strong routing guidance. It lacks any explicit when-not or prerequisite statement, so it stops short of the top band.

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 readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real value by disclosing what the response contains — header with customer, dates, status and lateness, order lines, and invoice with payments and outstanding amount.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences: purpose first, example questions second, return shape last. No filler and every sentence carries distinct 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?

An output schema exists, so return values need not be specified, yet the description still sketches them. For a single-parameter read tool, an agent has everything needed to select and call 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?

Schema coverage is 100% and the single parameter is already documented with format examples ('SO-1042', accepts '1042'). The description repeats the same example rather than adding syntax or edge-case meaning, so baseline 3 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?

Names a specific verb and resource ('Get the full status of one sales order') and scopes it to a single order, which cleanly separates it from list_overdue_orders and get_customer_balance.

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?

Two concrete example phrasings ("What's the status of order SO-1042?", "Has SO-1509 been invoiced or paid?") make the use case unambiguous. It stops short of naming which sibling to use for aggregate or overdue views, so it is clear context rather than explicit routing.

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 readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds genuinely useful behavior beyond that: which fields come back (quantity, reorder level, shortfall, 90-day units sold), the sort order (most critical first) and the 50-row cap.

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?

Front-loaded with the purpose in the first line, followed by examples and then return/sort details; every sentence carries information. The wrapped example list is slightly long but earns its place by clarifying filter usage.

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 read-only, zero-required-parameter lookup with an output schema and full annotation coverage, nothing an agent needs is missing: it knows the trigger questions, the filter surface, the returned fields and the result ordering/cap.

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 all three parameters are already documented with examples. The description's example questions loosely illustrate the query filter but add no syntax, matching behavior or empty-string semantics beyond the schema, so the baseline 3 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?

States a specific verb and resource ('Look up product stock levels') and immediately grounds it in concrete example questions. An agent can distinguish this from the sibling lookups (order status, customer balance, overdue orders, KPIs) without opening any schema.

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 three example questions map cleanly onto the available filters (free-text search, below-reorder, category), giving clear context for when to call it. It stops short of explicitly naming what to use instead if the user wants order-level or supplier-level data, so a 4 rather than a 5.

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 readOnly/idempotent/non-destructive/closed-world, so safety is covered; the description goes further by disclosing result ordering ('sorted by days late'), a hard row cap ('max 50 rows'), and an aggregate ('total value of the late orders'). It does not say what happens when more than 50 orders are late (silent truncation vs. error), which is the one behavioral detail an agent would still want.

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?

Front-loaded with the definition, then usage intents, then output behavior. Three short blocks, each earning its place, with no restatement of the title or name.

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?

Output schema exists and annotations cover safety, so the description only needs purpose, routing, and output-shape hints — all present. Nothing an agent needs to call this tool correctly 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 clear per-parameter descriptions, so baseline is 3. The example 'Show orders more than 14 days late' and the customer-specific example do implicitly illustrate how customer and min_days_late behave, but no additional format, default, or edge-case semantics are added 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?

States a specific verb and resource plus a precise business definition: 'sales orders that are late: promised date passed but not yet delivered.' That definition cleanly separates it from siblings like get_order_status (single order lookup) and get_kpi (aggregates), which an agent can disambiguate without opening a schema.

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 'Use for ...' clause is followed by three concrete user phrasings, including a customer-scoped one, which maps intent to tool effectively. It stops short of naming when NOT to use it or which sibling to pick for near-miss intents (e.g. a single order's status), leaving that inference to the agent.

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