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

With no annotations, the description carries the full burden and does well: it discloses validation behavior (capacity and maintenance checks), idempotency, warning semantics (cross-city vehicle, driver hours, fuel, cold-chain mismatch), and that errors propose alternatives. It stops short of stating permission requirements or whether a failed validation rejects the assignment outright.

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, then compact Args and Returns blocks. The Returns block is somewhat redundant given an output schema exists, but it is short and information-dense rather than padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers purpose, parameters, validation behavior, warning categories, and failure behavior. Since an output schema exists, the return explanation is a minor duplication rather than a gap; only explicit permission/precondition details are 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 0%, but the two parameters are named clearly and the description compensates with concrete example formats ("SHP-1007", "TRK-105") that the bare string schema lacks. More than adequate for a two-parameter tool.

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 ('Assign an own-fleet vehicle to a shipment') and scopes it to own-fleet, which implicitly separates it from the carrier-related siblings (list_carriers). An agent can distinguish this from track_shipment or list_vehicles immediately.

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?

Usage is implied by the verb and the own-fleet scoping, but there is no explicit when-to-use or when-not guidance, and no routing to an alternative for non-own-fleet assignments. It never says what to do when capacity or maintenance checks fail beyond 'errors suggest alternative vehicles'.

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 load. It discloses that this is a read-style lookup and describes the shape and semantics of the returned item fields (shortfall, low_stock, open_po), but says nothing about permissions, scoping restrictions, or behavior when the result set is large. An output schema exists, so reciting return fields adds less value than it appears.

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 purpose sentence followed by structured Args/Returns blocks, so the agent can parse it quickly. The Returns block restates information already carried by the output schema, which is mild redundancy, but nothing is bloated or buried.

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 three-optional-parameter read tool with an output schema available, the description covers invocation semantics and result contents adequately. It omits anything about permission requirements, rate/cost behavior, or result-size limits when all SKUs and warehouses are requested, which are the remaining gaps.

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 0%, so the description must compensate, and it does: each of the three parameters is explained with concrete value formats ('SKU-107', 'WH-BLR'/'BLR'/'Bangalore'), a fragment-matching convention for product names, and the meaning of empty/default values. This is exactly what the schema fails to provide.

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 ('Check stock levels per SKU and warehouse') and enumerates the payload of the result (low-stock flags, open purchase order), which clearly separates it from write-side siblings like create_reorder. It does not explicitly name a sibling it replaces, so it stops short of the top band.

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 invocation context for each parameter (empty string means all SKUs / all warehouses) and defines low_stock_only operationally, which is useful. However, it never says when to prefer this tool over alternatives such as get_kpis or create_reorder, and there are no exclusions or prerequisites stated.

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 and does so well: it discloses idempotent/retry-safe behavior, the duplicate-detection contract, and the auto-quantity side effect (qty=0 tops stock to 2x reorder point, min standard reorder qty). It omits permission requirements and any downstream effects (supplier notification, inventory mutation), keeping it short of a 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?

Front-loaded with the action and the retry-safety guarantee, then cleanly sectioned into Args and Returns. The Returns block restates what the output schema already declares, which is mild redundancy, but nothing else is padded.

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 3-parameter mutation tool with no annotations, the description covers action, idempotency, duplicate handling, and every parameter's semantics. An output schema exists, so the Returns summary is a bonus rather than a necessity, and no information an agent needs to call it 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 description coverage is 0%, so the description must compensate, and it does for all three parameters: sku format example, warehouse_id accepting ID/code/city, and detailed qty semantics including the default 0 = automatic behavior. This is meaningfully more than the bare integer/string types 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?

States a specific verb and resource ("Raise a purchase order to replenish a SKU at a warehouse") with the scope of the action. It is clearly distinguishable from every sibling, none of which create purchase orders; the closest siblings (check_inventory, list_shipments) are read operations on adjacent 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 description gives real usage context: it is safe to retry, and an existing open PO is returned with duplicate=true rather than double-ordering. It stops short of explicitly naming when-not-to-use or a competing alternative tool, but no sibling overlaps this action, so the routing gap is minor.

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 behavioral burden, but it only lightly implies a safe read via 'snapshot' and states the return wrapper 'KPI dict with status="ok"'. It says nothing about permissions, caching/refresh semantics, or whether the snapshot is real-time — gaps that matter for a monitoring tool.

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 metric list is front-loaded and the description is short. The 'Returns: KPI dict with status="ok"' line is largely redundant given an output schema exists, which is the one wasted fragment.

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 read tool with a full output schema and no annotations, the description is nearly sufficient: it tells the agent what metrics come back and that the call is a snapshot. The missing piece is when to prefer this aggregate over the sibling list/status tools.

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 takes zero parameters, so the baseline is 4. There is nothing for the description to disambiguate, and the enumerated metric names usefully pre-announce the shape of the payload the agent will receive.

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 resource (network health KPIs) and enumerates the exact metrics returned (on_time_rate, in_transit, delayed, exceptions, delivered_today, low_stock_skus, fleet_utilization, open_pos, critical_active). This is far more concrete than a tautology, though it never contrasts itself with siblings like check_inventory or track_shipment, which also surface operational status.

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?

There is no explicit when-to-use guidance, no prerequisites, and no mention of alternatives. An agent must infer that this is the dashboard/aggregate call rather than one of the shipment- or inventory-specific siblings; the description does nothing to route that decision.

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 behavioral burden. It discloses the return envelope ('status', 'count', 'carriers') and field meanings, which is useful, but says nothing about auth requirements, rate limits, caching/freshness, or whether the carrier set is static — mild gaps for a read-only listing.

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?

Purpose and usage are front-loaded in the first sentence, and the return block is compact. The 'Returns:' section partially duplicates the existing output schema, keeping it just short of maximally 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, parameterless listing tool with an output schema already present, the description covers what the tool is, what it returns, and why an agent would call it. Nothing needed to invoke it 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?

The tool takes no parameters, so there is nothing to disambiguate; the baseline for a 0-param tool is 4. The description instead spends its detail budget on the returned fields, which is the right trade-off.

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 ('List carrier partners') and enumerates the exposed fields (modes, INR rate card, reliability, average speed). No sibling tool deals with carriers, so the scope is unambiguous against list_shipments, list_warehouses, list_vehicles, etc.

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?

'use for quoting and choosing a carrier' gives a concrete use context, which is more than most list tools offer. It stops short of naming alternatives or stating when not to use it, but for a zero-param read tool the guidance is adequate.

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 burden. It discloses the sort order and the response shape with is_late/delay_hours, which is useful. However, it doesn't state read-only nature explicitly, permission requirements, or pagination behavior (only a limit default).

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 core action and sort order, then organized Args/Returns. Slightly verbose with the multi-line enum listing but every element is informative.

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?

Even without an output schema-explain requirement (it has one, though the description still describes the wrapper), the description covers filtering, sorting, and return shape adequately. Missing only explicit safety/read-only statement and cross-sibling guidance.

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 0%, so the description must compensate – and it does well: it enumerates status values including the 'active' pseudo-value, explains city alias matching across origin/destination/current city, and gives the limit default. Only priority lacks an explicit default note (empty = all is stated).

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+resource ('List shipments') and adds the implicit sort order (active first, critical first, then earliest promised delivery), which distinguishes it from track_shipment and update_shipment_status.

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?

Usage is implied by the filtering args (status/city/priority/limit), but there is no explicit 'when to use vs track_shipment/shipment_history' guidance or exclusions. The agent can infer this is a filtered list, but the sibling routing is left to inference.

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 exist, so the description carries the full behavioral burden. It implies a safe read and enumerates returned fields, but says nothing about pagination, result limits, permissions, or ordering for a list tool, leaving real gaps against the no-annotation baseline.

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 purpose sentence followed by clean Args/Returns blocks with no filler. The Returns block largely restates the existing output schema, which is mild redundancy, but it is not verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With only two optional parameters and an output schema already covering the return shape, the description supplies everything an agent needs to invoke the tool correctly. Only the missing behavioral details (limits, ordering) leave a small residual 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?

Schema description coverage is 0%, so the schema contributes only titles and defaults. The description compensates by enumerating the status values (available, on_route, maintenance) and clarifying that city accepts a name or alias, which is meaningful added 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?

States a specific verb and resource ('List own-fleet vehicles') plus the exact data surfaced (capacity, load, driver hours, fuel). 'Own-fleet' implicitly separates it from list_carriers, though no sibling is named explicitly, keeping it just short of a 5.

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?

Filter semantics are implied through the Args block ('Empty = all' for status and city), which tells the agent how to broaden results, but there is no statement of when to choose this over list_carriers, track_shipment, or other listing tools. Usage is inferable but not guided.

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. 'List' implies a safe read, and the return shape is disclosed, but there is no statement about pagination, ordering, result-size limits, or freshness of the utilisation/low-stock figures. Adequate but thin for an unannotated tool.

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 lines, front-loaded with the resource and its fields. The 'Returns:' block is arguably redundant with the output schema, but it is compact and does not bury the 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 zero-param read tool with an output schema already present, the description supplies what is needed: the resource and the fields each warehouse carries. Only the return-shape line duplicates the output schema, and nothing about result volume or pagination is stated.

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 takes zero parameters, so per the rubric the baseline is 4; there is no parameter semantics to explain beyond the implicit 'no filtering available' constraint, which the description does not state but the empty schema makes obvious.

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 ('List') and resource ('warehouses') and even enumerates the fields returned (city, coordinates, utilisation %, cold-chain capability, low-stock line count). It is clearly distinct from the shipment/vehicle/carrier siblings, though it never explicitly says so.

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 when-to-use statement, no alternatives, no exclusions. For a zero-parameter listing tool the intended use is largely self-evident, so the guidance is implied rather than absent, but nothing in the text routes the agent here versus check_inventory or get_kpis.

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 behavioral burden. It discloses the semantic content of the response and implies a read-only operation, but says nothing about ordering guarantees, pagination or result caps for long trails, or any permission requirements — meaningful gaps for a history endpoint.

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 purpose sentence is front-loaded with the key scope words, and the Args/Returns blocks are terse and scannable. No filler or repetition.

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 single-parameter read tool with an output schema present, the description covers purpose, the input format, and a sample response, so it is largely self-sufficient. The only shortfall is the absence of any note on result size or paging for long event trails.

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 0%, so the description has to compensate and it does: it gives the expected ID format example ("SHP-1003"), which the bare string schema does not. Only one parameter exists and no additional qualifiers (date range, filters) are hinted at.

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 resource and scope: a full chronological event trail (scans, checkpoints, delays, assignments) for one shipment. This clearly differs from a current-status tool like track_shipment, but the description never names or contrasts with any sibling, so the agent must infer the boundary.

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?

Usage is only implied by the words 'full chronological event trail', which suggests historical/audit retrieval versus a live-tracking sibling. There is no explicit when-to-use, when-not-to-use, or named alternative, so the routing guidance is left to inference.

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 exist, so the description carries the full load, and it does disclose real behavior: accepted ID variants ('SHP-1001', 'shp1001', '1001'), that recent_events returns only the latest 5 newest-last, and the miss behavior (status="error" with suggestions). It omits auth/permission needs and rate limits, which keeps it from a 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?

Front-loaded with the purpose and usage trigger before the Args/Returns blocks, and every sentence carries information. The Returns block restating 15 output fields is somewhat redundant given an output schema exists, mildly diluting conciseness.

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 single-parameter read tool with an output schema, the description supplies the identifier format, the priority trigger, and error behavior. It is essentially complete, with only minor gaps around permissions and any pagination/limit nuance for recent_events.

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 0%, so the schema provides no parameter meaning at all. The description compensates fully for the single parameter by giving a concrete example ID and documenting that normalized/short forms are also accepted, which is information an agent could not get from 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 ('Track a shipment') and enumerates the exact facets returned: status, location, ETA vs promised delivery, carrier, vehicle, recent events. It implicitly separates itself from list_shipments via 'a specific shipment or order' but never names a sibling, so it stops short of a 5.

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?

'Use this first whenever the user mentions a specific shipment or order' is an explicit trigger condition with a priority ordering relative to other tools. It gives no when-not guidance or named alternative (e.g. list_shipments for broad queries), so it is clear context without exclusions.

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 and does reasonably well: it discloses a side effect beyond the status change (a history event is logged), specifies that the note is persisted as the shipment note, and that invalid input returns an error listing valid values. It stops short of stating permissions, reversibility, or idempotency, which matters for a mutation tool.

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 one-line purpose is front-loaded, and the Args/Returns block is tightly formatted with one line per parameter and no filler. Every sentence carries information an agent needs to invoke the tool correctly.

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 four-parameter mutation tool with no annotations, the definition covers purpose, all parameters, the side effect, and the return shape, so an agent has what it needs. The only gap is the absence of any explicit routing guidance against the many read-oriented sibling tools.

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 0%, so the description must compensate and it does: it documents all four parameters with an ID format example ('SHP-1002'), the complete closed set of valid status values (absent from the schema, which has no enums), and the default behavior of city when omitted.

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 ('Change a shipment's status') and adds the important side effect that a history event is logged, which an agent cannot infer from the name alone. It does not explicitly differentiate itself from siblings such as track_shipment or shipment_history, but the mutation-plus-audit purpose is 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?

Usage is implied rather than stated: the examples ('mark delayed, delivered, exception') show the intended scenario, but there is no explicit when-to-use vs sibling guidance (e.g. vs track_shipment, which appears read-only) and no stated prerequisites or exclusions.

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