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

No annotations provided, so description carries full burden, but provides minimal behavioral disclosure. Does not state whether this is reversible, idempotent, whether it triggers notifications, or what state transition occurs (open→acknowledged vs. acknowledged→closed).

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?

Extremely concise (4 words) and front-loaded with the action verb. No redundancy, though brevity comes at the cost of behavioral transparency. Structure is efficient but possibly underspecified given the mutation nature 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?

Inadequate for a state-changing operation with zero annotations. Lacks explanation of side effects, return values (though no output schema exists), error conditions (e.g., already-acknowledged alerts), or business logic implications of the acknowledgment action.

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 has 100% description coverage for both parameters, establishing baseline of 3. Description adds no additional semantic context (e.g., format constraints on alertId, whether acknowledgedBy must match current user), but doesn't need to compensate for schema gaps.

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?

Clear verb ('Acknowledge') and resource ('IoT alert'), distinguishing it from sibling 'get_alerts' by action type. Mention of 'IoT' adds domain context. However, it lacks specificity about what acknowledgment entails (resolution vs. ownership assignment).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use versus alternatives (e.g., should I create a maintenance task instead of acknowledging?), prerequisites (can I acknowledge resolved alerts?), or exclusion criteria. Agent must infer usage from verb alone.

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 full burden but only implies a write operation via 'Create'. It omits critical behavioral details: whether the operation is atomic, if it triggers notifications to assigned technicians, error handling for invalid assetIds, or what the return value 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?

Extremely concise at 7 words in a single sentence. While efficiently worded without redundancy, it is arguably underspecified for an 8-parameter creation tool with no output schema.

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 mutation tool with 8 parameters (7 required) and no output schema, the description is insufficient. It fails to describe the return value, success/failure states, or side effects like notifications generated in the CMMS system.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the structured schema adequately documents all 8 parameters including enums for taskType and priority. The description adds no parameter-specific guidance, meeting the baseline for high-coverage schemas.

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 (Create) and resource (maintenance task) with system context (CMMS). However, it fails to differentiate from sibling tools like `get_work_orders` or explain when to use maintenance tasks versus work orders in the CMMS workflow.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance provided on when to use this tool versus alternatives like `get_work_orders`, prerequisites such as asset existence validation, or required conditions for the scheduled/due dates.

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. While it mentions filtering, it fails to clarify that this is a read-only operation (crucial given the mutating sibling acknowledge_alert), does not describe the return format, and omits pagination or rate limiting details.

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 consists of two efficient sentences with zero waste. The purpose ('Get IoT alerts') is front-loaded in the first sentence, while the second sentence immediately follows with filtering capabilities.

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 low complexity (3 simple optional parameters, no nested objects) and lack of output schema or annotations, the description provides minimum viable coverage of the tool's function. However, it lacks details about return values, scope limitations, or operational constraints that would be helpful for a querying 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?

The input schema has 100% description coverage, establishing a baseline of 3. The description maps closely to the schema by listing the three filterable fields (severity, acknowledged status, device) but adds minimal semantic depth beyond what the schema already provides.

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 states a clear verb ('Get') and resource ('IoT alerts'), and the resource type distinguishes it from sibling tools like get_devices or get_assets. However, it does not explicitly differentiate from acknowledge_alert, which is alert-related but performs a mutation action.

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 mentions filtering capabilities but provides no guidance on when to use this tool versus alternatives like get_devices or acknowledge_alert, nor does it mention prerequisites or conditions for optimal use.

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 lacks information about pagination, what happens when both parameters are provided, authentication requirements, error handling, or the structure of returned assets.

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 consists of two efficient sentences with no redundancy. The first establishes system context (CMMS) and action; the second summarizes parameter capabilities. Every sentence earns its place, though brevity comes at the cost of completeness given missing annotations.

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 complexity of the CMMS domain (evidenced by numerous sibling tools for equipment, devices, sensors, and work orders) and the absence of annotations or output schema, the description should clarify what constitutes an 'asset' and how it relates to similar entities. It does not.

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%, establishing a baseline of 3. The description adds marginal value by implying an 'or' relationship between filtering by status versus retrieving a specific assetId, suggesting alternative usage modes not explicitly stated in the schema constraints.

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 states 'Get assets from CMMS system,' providing a clear verb and resource with system context. However, it fails to distinguish 'assets' from sibling tools like get_equipment, get_devices, or get_sensors, which appear to serve similar functions in the CMMS domain.

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 mentions filtering capabilities ('Can filter by status or get specific asset') but provides no guidance on when to use this tool versus alternatives like get_equipment or get_devices, nor does it indicate prerequisites or mutual exclusivity of parameters.

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 provided, so description carries full disclosure burden. While 'Get' implies a read operation, there is no information about pagination, rate limits, return format, or error states. Insufficient for a tool in a complex system with many related endpoints.

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?

Extremely concise with two short sentences. However, given the lack of annotations and presence of many sibling tools, this brevity comes at the cost of necessary context. Structure is front-loaded but undersized for the tool's complexity.

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?

Inadequate for the complexity implied by 11 sibling tools and no annotations or output schema. No explanation of how devices relate to sensors/assets, no pagination details, and no return value description. The description meets only the bare minimum for a standalone 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 100%, so the schema already documents both parameters. The description confirms filtering is optional (consistent with 0 required parameters), but adds no syntax details, format examples, or semantic meaning beyond the schema definitions.

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 the basic action ('Get') and resource ('IoT devices'), but fails to distinguish from siblings like get_sensors, get_assets, or get_equipment which may overlap conceptually in an IoT system. Lacks specificity on what constitutes a 'device' versus these related resources.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like get_sensors or get_assets. The phrase 'Can filter by status or type' describes capability, not selection criteria or prerequisites for use.

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. It mentions the external MES system dependency but fails to disclose read-only nature, error handling behavior, rate limits, or return structure.

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 efficient sentences with no waste. The first sentence establishes purpose and system context; the second explains capabilities. 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?

Adequate for a simple 2-parameter getter with complete schema documentation, but lacks differentiation from similar sibling tools and behavioral details that would help an agent handle errors or understand the MES integration.

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?

With 100% schema coverage, the baseline is 3. The description adds valuable semantic context by mapping the usage patterns to parameters: 'filter by status' corresponds to the status parameter and 'get specific equipment' corresponds to equipmentId, clarifying the intended use of each.

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), resource (equipment status), and source system (MES). However, it does not differentiate from siblings like get_assets or get_devices which may overlap conceptually.

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 implies usage patterns ('filter by status or get specific equipment'), indicating the two optional parameters are mutually exclusive modes. However, it lacks explicit guidance on when to prefer this over get_assets or get_devices.

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. While 'Get' implies a read-only operation, the description lacks details about pagination, rate limits, data retention windows, or what specific maintenance events constitute 'history' in the return payload.

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 consists of two efficient sentences with zero redundancy. The first sentence establishes purpose and system context, while the second summarizes filtering capabilities. Every word earns its place without unnecessary elaboration.

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-parameter query tool with full schema documentation and no output schema, the description meets minimum viability. However, given the absence of annotations and output schema, it could be strengthened by clarifying what maintenance history entails (e.g., completed work orders, repairs) to distinguish it from sibling maintenance 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?

With 100% schema description coverage, the schema already documents all three parameters (assetId, startDate, endDate) adequately. The description adds minimal semantic value beyond grouping them as 'asset or date range' filters, meeting the baseline expectation when schema coverage is high.

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 resource ('maintenance history from CMMS system'), clearly identifying the tool's function. However, it does not explicitly differentiate from the sibling tool 'get_maintenance_tasks', which could cause confusion about whether to query historical records versus active task lists.

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 mentions filtering capabilities ('Can filter by asset or date range') but provides no explicit guidance on when to use this tool versus siblings like 'get_maintenance_tasks' or 'get_work_orders', nor does it mention prerequisites such as requiring valid asset IDs from the CMMS system.

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 full burden for behavioral disclosure but offers minimal details. It does not specify pagination behavior, what fields are returned, or the effect of calling without filters (return all tasks?).

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 two-sentence structure is appropriately brief and front-loaded with the core purpose. However, it is incomplete in that it fails to mention the 'assetId' filter parameter available in the schema.

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?

Adequate for a simple retrieval operation with well-documented schema parameters, but lacks critical context regarding the relationship between maintenance tasks, work orders, and maintenance history, which is essential for correct tool selection given the sibling set.

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%, establishing a baseline of 3. The description enumerates three filters (status, priority, type) but omits 'assetId', adding no semantic depth beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the action ('Get') and resource ('maintenance tasks') with source context ('CMMS system'). However, it does not distinguish from sibling tools like 'get_maintenance_history' or 'get_work_orders', which appear to retrieve similar operational data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides no guidance on when to use this tool versus alternatives like 'get_work_orders' or 'get_maintenance_history', nor does it mention prerequisites or rate limiting. The agent must infer usage from the resource name alone.

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 but fails to deliver. It does not indicate whether the operation returns a list or single object, pagination behavior, rate limits, or authentication requirements. The word 'Get' implies read-only access but lacks explicit confirmation of safety.

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 consists of two efficient sentences with no filler. The first sentence establishes the core purpose and system context, while the second highlights key functionality. It avoids tautology and wastes no words, though it could sacrifice some brevity for additional behavioral context.

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 absence of annotations and output schema, the description should explain expected return values, pagination, and differentiate from similar siblings like 'get_work_orders'. It mentions 'MES system' (Manufacturing Execution System) which provides domain context, but remains incomplete regarding behavioral traits and tool selection criteria.

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%, establishing a baseline of 3. The description mentions status filtering which aligns with the schema, but does not add syntax details, format examples, or explain the relationship between the optional 'orderId' (specific lookup) and 'status' (filtering) parameters beyond what the schema already provides.

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 action ('Get'), resource ('production orders'), and source system ('MES system'). However, it loses a point for failing to distinguish from the similar sibling tool 'get_work_orders', which could cause selection ambiguity in a manufacturing context where production orders and work orders are distinct concepts.

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 mentions filtering capability ('Can filter by status') but provides no explicit guidance on when to use this tool versus alternatives like 'get_work_orders', nor does it specify prerequisites or conditions where this tool should be preferred over other retrieval tools in the sibling list.

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 but offers minimal insight. It does not indicate whether queries are expensive, if results are real-time or cached, pagination behavior, or what happens when no readings match the filters. 'Get' implies read-only, but safety/performance characteristics are missing.

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 consists of two efficient sentences with the primary purpose front-loaded. While the second sentence merely lists filtering capabilities already evident in the schema, there is no redundant or wasteful language.

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

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

Given the simple flat schema with three optional parameters and no output schema, the description provides minimally viable context. However, lacking annotations and output specification, it omits important behavioral context that would help an agent predict result sets and handle empty responses or large data volumes.

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 the input schema has 100% description coverage, the baseline score is 3. The description essentially summarizes the three filter parameters (sensor, status, time range) without adding significant semantic context—such as explaining that 'hours' refers to a trailing window from current time, or that 'status' represents computed severity levels.

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 action ('Get') and resource ('sensor readings') and specifies the system context ('IoT system'). It implicitly distinguishes from sibling 'get_sensors' by specifying 'readings' versus sensor metadata, though it could more explicitly clarify the temporal/data nature of the readings.

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 mentions available filters but provides no guidance on when to select this tool over siblings like 'get_alerts' (which may also return critical sensor states) or 'get_sensors' (which may include current values). No prerequisites, exclusions, or decision criteria are provided.

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

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

No annotations are provided, yet the description discloses minimal behavioral traits. It omits: what happens when called with no arguments (returns all sensors?), pagination behavior, return format, and whether this is a cached or real-time operation. For a read operation with zero required parameters, this lack of behavioral context 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?

Two short sentences with no redundant words. The structure front-loads the core purpose in the first sentence and lists capabilities in the second. Efficient, though sparse on information density.

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?

Inadequate given the tool ecosystem complexity (11 sibling tools including similar getters) and lack of annotations/output schema. The description fails to clarify scope boundaries, distinguish from get_sensor_readings, or explain the 'all optional' parameter behavior (empty query 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?

Schema description coverage is 100%, establishing a baseline of 3. The description lists the three filterable fields ('type, status, or equipment') but adds no semantic depth beyond what the schema already provides (e.g., explaining equipment relationships or enum value implications).

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 the basic action ('Get sensors') and domain ('IoT system'), but fails to differentiate from similar sibling tools like get_sensor_readings (which likely retrieves time-series data vs. this tool retrieving sensor metadata/configurations) or get_devices/get_equipment.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides no guidance on when to use this tool versus alternatives like get_sensor_readings or get_devices. The phrase 'Can filter by...' describes capability rather than usage strategy or prerequisites.

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 fails to mention whether the operation is read-only, pagination behavior, rate limits, or what occurs when no filters are applied (returns all records? limited set?). Only the filtering capability is noted.

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 consists of two efficient sentences with zero waste. The first establishes the core operation and resource; the second immediately clarifies filtering capabilities. Appropriately sized for the tool's complexity.

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

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

Given the simple 2-parameter schema with full coverage and no output schema, the description meets minimum viability but leaves gaps regarding unfiltered query behavior, return format, and pagination. Adequate for basic selection but lacks richness expected for a production MES integration.

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%, documenting both parameters adequately. The description adds semantic context by confirming these are 'filter' parameters rather than identifiers for specific records, but does not elaborate on parameter relationships or data formats beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear verb ('Get') and resource ('work orders from MES system'), identifying the specific system context. However, it does not explicitly differentiate from sibling tool 'get_production_orders' despite mentioning production orders as a filter criterion.

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 patterns by noting filtering capabilities ('Can filter by status or production order'), but provides no explicit guidance on when to use this versus alternatives like 'get_maintenance_tasks' or 'get_production_orders', nor prerequisites for filtering.

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