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

All annotations are false, providing no safety hints. The description compensates by fully disclosing file behavior (creates/append/replaces with overwrite=true), the transacted vs ack_mode precedence with warning, and generated code structure (activemq:Caller for ack modes). This is far richer than the minimal annotation info.

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 five sentences, each carrying essential operational information. It is logically structured and front-loaded with the main action, though slightly dense due to the detailed code-generation specifics. No wasted words.

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 11 parameters, nested objects, and no output schema, the description covers file handling, destination types, ack/transacted semantics, and conflict resolution. However, it does not mention return values or error scenarios, which could leave minor uncertainty about invocation outcomes.

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

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

Schema coverage is 100%, but the description adds critical meaning: conditional requirements (subscriber_name required when durable=true, consumer_group for virtual-topic), transacted overriding ack_mode, and how parameters map to generated @activemq:ServiceConfig fields. This significantly enhances schema descriptions.

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 verb and resource: 'Add a message Listener service... to listener.bal.' It distinguishes itself from siblings by specifying it creates a declarative service with @activemq:ServiceConfig and onMessage, which is unique compared to mq_add_queue, mq_add_topic, and mq_set_ack_mode.

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 on when to use the tool (adding listeners for queue/topic/virtual-topic destinations and handling ack modes), but it does not explicitly mention alternatives or when not to use it. However, the distinct purpose is implied sufficiently.

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?

The description discloses key behavior beyond the annotations: it creates a specific module file and functions, uses Client.sendMessage/receiveMessage, and explicitly states the overwrite condition ('Does not overwrite unless overwrite=true'). This adds meaningful behavioral detail even though annotations indicate readOnlyHint=false and destructiveHint=false.

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 tight, three-sentence summary that is front-loaded with the primary purpose, then details the file/function generation and the overwrite guard. Every sentence contributes value without verbosity.

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 covers the tool's purpose, generated artifacts, and key behavior (overwrite). While it does not explain failure modes or build integration, it is complete for a focused module-generation tool among a broader toolset. No output schema exists, so return values are not expected to be documented.

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 each parameter having a clear description. The tool description adds minimal extra meaning to parameters (e.g., 'point-to-point' for queue_name, overwrite behavior), but these are already largely present in the schema. Thus a baseline of 3 is appropriate.

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 action: 'Add a queue helper module to an existing project', and differentiates it by specifying the JMS queue (point-to-point) and the exact files/functions created. This distinguishes it from sibling tools like mq_add_topic and mq_add_listener.

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 solid usage context ('to an existing project', 'wired to the JMS queue') and clearly scopes it to queue-based point-to-point messaging. It does not explicitly name alternative tools for topics/listeners, but the context is clear enough for an agent to select correctly.

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

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

Beyond annotations (readOnly=false, destructive=false), the description discloses key behaviors: it creates a specific file path, generates a publish function, and has an overwrite guard ('Does not overwrite unless overwrite=true'). It also notes that subscribers should be created via mq_add_listener, providing clarity about side effects and system architecture.

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 three sentences, front-loaded with the core purpose, and every sentence adds value: file creation, function behavior, subscriber alternative, and overwrite behavior. No fluff 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?

Given no output schema and moderate complexity (7 params, code generation), the description covers essential context: what is created, how subscribers are handled, and overwrite behavior. It doesn't mention return values or error handling, but for selection and invocation, it provides sufficient context. It also points to the sibling tool for listener creation, improving completeness.

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 baseline is 3. The description adds meaning beyond the schema by explaining how topic_name maps to the file and function (publish<Name>() to 'topic://<topic>') and how durable/subscriber_name relate to listener creation. This enhances parameter understanding without redundancy.

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 'Add a topic (pub/sub) helper module to an existing project' and specifies exactly what is created (modules/<topic>/<topic>.bal with a publish<Name>() function). It distinguishes from siblings by explicitly mentioning mq_add_listener for subscribers and implying queue vs topic via 'pub/sub'.

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 clear context: use this to add a topic publisher module to an existing project. It names the alternative tool for creating subscribers ('use mq_add_listener with type=topic'), but does not explicitly exclude other cases like queues or when not to use it. Still, the guidance is actionable.

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 indicate idempotent and non-destructive behavior; the description adds that it verifies the Ballerina toolchain first and does not modify source files. It also discloses that it reports success or diagnostics, providing useful behavioral context beyond the annotations.

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 concise sentences, front-loaded with the core action. Each sentence adds value: what it does, the toolchain check, and the offline behavior with the non-modification guarantee.

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 a build tool with no output schema. It covers prerequisites (scaffolded project, toolchain check), behavior (offline, no source modification), and return value (success or diagnostics).

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 baseline is 3. The description mentions offline=true, but this exactly restates the schema description. No additional parameter meaning is provided.

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 runs `bal build` in a scaffolded project and reports success or compiler diagnostics. This specific verb+resource distinguishes it from siblings like mq_scaffold_project (create) and mq_deploy_project (deploy).

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

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

It provides clear context by specifying 'in a scaffolded project' and the offline option for cached dependencies, implying when to use it. It does not explicitly name alternatives or exclusions, but the context is sufficient.

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?

The description richly discloses behavior: returns PID, watches for early crash for wait_ms, reports output, composes service URL if service_port given, and reveals that the process keeps running after return. This goes well beyond the annotations (readOnlyHint=false, idempotentHint=false) and adds critical operational context.

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?

Four sentences, each adds distinct value. Front-loaded with the core action, then behavior, optional output, and persistence. No fluff or redundancy.

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?

Despite no output schema, the description explains the return values (PID, optional service URL) and the asynchronous nature of the process. It also notes toolchain verification, making it complete for an agent to invoke correctly.

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

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

Schema covers all parameters (100% coverage), but the description adds context by explaining the functional role of wait_ms (watch for early crash) and service_port (compose service URL), enhancing the schema descriptions. Baseline is 3, and this pushes to 4.

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 the specific action: 'Run `bal run` for a scaffolded project as a detached background process and return its PID.' It clearly distinguishes from sibling tools like mq_build_project (build) and mq_scaffold_project (scaffold) by focusing on deployment/execution.

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 after scaffolding and references a scaffolded project, but does not explicitly contrast with alternatives like mq_build_project or state when-not to use. It provides context (detached process, verifies toolchain) but lacks explicit exclusions or alternative 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?

Despite light annotations, the description discloses important behavioral details: it writes files to disk, lists every artifact generated, calls out conditional generation based on include_listener and transacted, and explains the conflict-resolution rule where transacted overrides ack_mode (with a warning). This goes well beyond the annotations and schema.

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

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

The description is long but packed with necessary detail about the many files and flags. It front-loads the core purpose and avoids filler. The lengthy file list is justified for a scaffolding tool, though it could be slightly tightened by moving implementation specifics into 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?

For a complex tool with 11 parameters, no output schema, and a dozen generated artifacts, the description covers the key generation rules, conditional files, and conflict handling. It explains what gets written, when, and how parameter interactions are resolved, making it sufficiently complete for an agent to invoke correctly.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds extra semantic value by linking specific parameters to generated files ('listener.bal ... when include_listener is set', 'transactions.bal when transacted is set') and clarifying the precedence relationship between transacted and ack_mode, which is not captured in individual parameter descriptions.

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 'MAIN tool' and states a specific verb and resource: 'Generate a complete, runnable WSO2 Integrator (BI) Ballerina project that integrates with ActiveMQ via the ballerinax/activemq connector.' It then enumerates the exact set of files created, making the tool's scope unmistakable and clearly distinguishing it from sibling tools that validate, add queues, or build/deploy.

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 'MAIN tool' marker and the comprehensive scaffold list establish that this tool is the entry point for creating a project. However, the description does not explicitly name alternatives or state when not to use this tool (e.g., 'for incremental changes use mq_add_queue'), so it lacks the explicit exclusions that would earn 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 indicate destructiveHint=true and readOnlyHint=false; the description adds rich behavioral detail: rewrites sessionAckMode, regenerates the affected onMessage, adds/removes the activemq:Caller parameter and acknowledge/commit+rollback calls, and edits a .bal file in place. No contradiction with annotations.

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?

Exactly four sentences, front-loaded with the primary action, then relevant details. Every sentence contributes: what, why, scope, and mechanism. No fluff or redundancy.

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 file-editing tool with no output schema, the description explains the what, why, how, and scope. It is sufficient for the agent to understand the operation. Not a 5 because it omits potential failure modes (e.g., file not found, malformed annotation), but given schema richness and annotations, it is quite complete.

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

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

Input schema has 100% description coverage for all 4 parameters. The description adds little beyond the schema: the service_name scoping ('Targets one service... or all services when omitted') is already present in the schema. Baseline 3 is appropriate as the schema carries the 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?

Starts with a specific verb+resource: 'Set/update the acknowledgement mode on listener service(s)'. It further details the mechanism (editing listener.bal, rewriting sessionAckMode, regenerating onMessage) and distinguishes itself from siblings like mq_write_config_toml and mq_add_listener by focusing on ack mode and source editing.

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 a clear context and exclusion: 'Ack mode cannot live in Config.toml (it is a compile-time constant), which is why this edits source.' This guides against using a configuration-based alternative. However, it does not explicitly state when not to use this tool or compare with other sibling tools beyond the Config.toml note.

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, and non-destructive. The description adds valuable behavioral details: TCP probe mechanics, support for failover URL forms, optional Jolokia web-console query, and graceful degradation. No contradiction with annotations.

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 three sentences, front-loads the primary purpose, and contains no unnecessary filler. Every sentence adds meaningful detail about behavior and constraints.

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 no output schema, the description covers key behavior well, including protocol handling and graceful degradation. However, it does not specify the exact return format, which is a minor gap for a validation tool that may produce a structured report.

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 baseline is 3. The description adds marginal context (e.g., 'TCP connectivity probe') but largely restates parameter meanings already present in the schema, such as URL forms and list_destinations behavior.

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

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

The description clearly states a specific action ('Check that an ActiveMQ broker is reachable') with a specific resource ('at the given OpenWire URL'). It distinguishes itself from sibling tools (scaffold, build, deploy) by focusing on validation and connectivity probing.

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 clearly implies use when validating broker connectivity or listing destinations. It does not explicitly mention when not to use it or name alternatives, but sibling tools are not direct alternatives, so the context is sufficiently clear.

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 destructiveHint=true and readOnlyHint=false, and the description adds 'Overwrites the existing Config.toml' which aligns with that. It also discloses a subtle behavior: ack_mode/transacted parameters are only written as comments, not actually affecting runtime behavior. This goes beyond the annotations and schema, providing valuable caution.

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 three sentences, each earning its place: the action, the table/parameters, and the critical caveat about ack_mode/transacted. It is front-loaded with the verb+resource and contains no fluff 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 config-writing tool with 8 parameters, no output schema, and strong annotations, the description covers the key aspects: what is written, to which file, and the overwrite behavior. It does not describe the return value or error scenarios, but given the tool's simplicity and the rich schema, this is adequate. The caveat about ack_mode/transacted adds necessary context for correct use.

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 covers 100% of parameters with detailed descriptions, so the baseline is 3. The description adds semantic nuance about how ack_mode and transacted are treated (as documented mirror comments), which is not fully obvious from the schema alone. This extra explanation helps the agent understand the real effect of those parameters.

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+resource: 'Write or rotate the broker connection Config.toml for an existing project.' It clearly states what the tool does and includes an explicit 'Overwrites the existing Config.toml' warning. This distinguishes it from sibling tools like scaffold or add queue, which operate on 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 description notes that the tool is for an existing project and that ack_mode/transacted are only mirror comments, implying that actual ack mode should be set via mq_set_ack_mode (a sibling tool). It does not explicitly name alternatives or state 'when not to use', but the context strongly guides the user away from using this tool for setting effective ack mode.

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