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 it only says 'Create a new K3s cluster definition' without explaining side effects, idempotency, or whether it triggers any infrastructure changes. It does not even clarify if this is a local metadata operation or a remote API call, leaving major behavioral unknowns.

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

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

The description is a single sentence with no waste, front-loading the core purpose immediately. It is appropriately concise for a simple create operation, though it sacrifices substance for brevity.

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 tool has 3 parameters, no output schema, no annotations, and multiple related siblings, the description is far too thin. It does not explain what 'definition' means in the context of K3s, what the user should expect after calling it, or whether it is a prerequisite for 'provision_cluster'. This creates a significant completeness gap.

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

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

The input schema provides 100% coverage with descriptions for all three parameters (name, description, k3s_version), so the baseline is 3. The tool description adds no extra parameter semantics beyond what the schema already states, hence no uplift.

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 specific verb ('Create') and resource ('K3s cluster definition'), which clearly indicates the tool's function. However, it does not explicitly differentiate itself from sibling 'provision_cluster', leaving ambiguity about whether this creates a real cluster or just a definition. The word 'definition' provides a subtle hint but could be clearer.

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 is provided on when to use this tool versus alternatives like 'provision_cluster' or 'list_clusters'. The description does not mention prerequisites, typical use cases, or exclusions, so the agent gets no help in selecting this tool.

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 must fully disclose behavioral traits. It mentions the deprovisioning prerequisite, but does not state whether deletion is irreversible, what consequences occur, or what the response looks like. This is insufficient for a destructive operation.

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

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

The description is a single concise sentence with no redundant words. It is well-structured and front-loaded, effectively conveying the core action and a key condition.

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 lack of annotations and output schema, the description should provide more context for a destructive tool. It only covers the prerequisite, omitting details about permanence, side effects, permissions, or expected outcomes, making it incomplete for safe and correct invocation.

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

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

The schema covers 100% of the single parameter (cluster_id) with a minimal description. The tool description adds no further meaning about the parameter, so the schema remains the primary source of information, leading to a baseline score of 3.

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 action ('Delete a cluster') with a specific resource, and the prerequisite ('must be deprovisioned first') adds essential context. It is easily distinguished from sibling tools like create_cluster or provision_cluster.

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 usage context by specifying a required precondition (deprovisioning before deletion). It does not explicitly name alternatives or exclusion cases, but the prerequisite effectively guides when it is appropriate to use this tool.

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 must disclose behavior. It merely says 'deploy,' which implies a mutating action, but offers no details about side effects, failure modes, blocking behavior, or required permissions.

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

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

The description is a single sentence that is concise but does not add significant value beyond the tool name. It is not verbose, but it is under-specified for a tool with a nested object parameter.

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 deployment action with no annotations, no output schema, and sparse parameter documentation, the description is incomplete. It does not explain required context like cluster existence, pod spec format, or post-deployment validation.

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 is sparse (two parameters, no descriptions) and schema coverage is 0%. The description does not mention or explain any parameter roles, leaving the agent without information about what cluster_id or pod_spec mean or how to construct them.

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 specific verb ('Deploy'), resource ('a Kubernetes pod'), and destination ('a cluster'). It clearly distinguishes from sibling tools (cluster management, node provisioning) as the only pod-deployment tool.

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 guidance on when to use this tool vs. alternatives, prerequisites (e.g., cluster must exist), or typical scenarios. The description only states the action without any contextual direction.

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 discloses the primary effect and resulting state, which is useful. But it omits details like whether the operation is destructive to data, whether it requires SSH (though schema hints at it), and if there are any side effects or prerequisites.

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

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

The description is a single, well-formed sentence with no redundant wording. It conveys the core action and result efficiently.

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 tool with only 2 params and no output schema, the description gives the essential purpose but lacks details about return values, async behavior, or workflow steps. It's adequate but not comprehensive.

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 parameters are already well-documented. The description adds no extra semantic meaning beyond what the schema provides, so a baseline score 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 uses a specific verb ('Remove') and resource ('K3s from a node'), and includes an outcome ('return to discovered state'). This clearly distinguishes it from sibling tools like provision_node or register_node.

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 usage is implied: if you want to deprovision a node, this is the tool. However, no explicit when-to-use, when-not-to-use, or alternative tools are mentioned.

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 for behavioral disclosure. It only states 'List all' and fails to mention that results are paginated via limit/offset, that the include_gpio parameter defaults to false, or that this is a read-only operation. The meaning of 'discovered' is also unclarified.

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

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

The description is a single, front-loaded sentence with no redundant words. It is as concise as possible while conveying the core 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?

The tool has 6 parameters, no annotations, and no output schema, making the description insufficiently complete. It omits any mention of filtering options, pagination, the structure of returned nodes, or the meaning of 'discovered', leaving an agent without enough context to invoke the tool effectively beyond a naive list call.

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 schema covers 67% of parameters with descriptions, so the baseline is fair. However, the description adds no parameter semantics beyond the operation name. It does not explain the pagination behavior of limit/offset, which lack textual descriptions in the schema, but the filter parameters (role, status, cluster_id) are adequately described there.

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 action (List) and the resource (all discovered Raspberry Pi nodes). It distinguishes from siblings like get_node_info, which targets a single node, and list_clusters, which lists clusters.

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 no guidance on when to use this tool versus alternatives such as get_node_info for specific node details or list_clusters for cluster-level views. It also does not mention available filters or pagination, leaving the agent without decision context.

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 indicates a read operation via 'Get' but does not explicitly state it is read-only, lacks side effects, or require any permissions. It also does not disclose behavior on missing clusters or error scenarios. This is a significant gap for a tool with no annotation support.

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

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

The description is a single, front-loaded sentence with no filler. It efficiently conveys the tool's purpose and key result areas.

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 tool's simplicity (one parameter, no output schema), the description adequately conveys what the tool returns ('nodes, workloads, and health'). However, it does not specify the structure of the returned information or set expectations for errors, which prevents a higher score.

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 schema covers the only parameter 'cluster_id' with 100% coverage, so the baseline is 3. The description adds no information about the parameter beyond what the schema already states.

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' with a clear resource 'detailed status of a cluster' and lists the content areas ('nodes, workloads, and health'). This distinguishes it from sibling tools like list_clusters (which lists clusters) and get_node_info (which targets a single node).

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 word 'detailed' implies this should be used when a more in-depth view than list_clusters is needed, but there is no explicit guidance on when to use this tool versus siblings, nor any mention of exclusions. Usage is only implied, not 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 must carry the behavioral burden, but it only says 'get detailed information' without disclosing whether this is a safe read-only operation, any permission requirements, potential errors (e.g., node not found), or side effects. It also fails to clarify what 'detailed' includes or whether the information is live or cached. The inclusion of an optional include_gpio parameter hints at behavior but is not explained in the description.

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

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

The description is a single, front-loaded sentence that states the primary action and resource. There is no wasted verbiage, and it is appropriately concise given the simple 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?

Although the schema covers parameters, there is no output schema, and the description does not explain what fields or data structure the agent can expect in the response. The phrase 'detailed information' is vague and does not enumerate node attributes like status, configuration, or metadata. With no annotations and no return-value description, the agent may be underprepared for the tool's actual output.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds no extra parameter semantics beyond what the schema already provides (node_id and include_gpio). Since the schema fully documents both parameters, the description does not need to compensate, but it also offers no added clarity.

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 'Get detailed information about a specific node' uses a specific verb ('get') and resource ('node'), clearly distinguishing it from sibling tools like provision_node or list_gpio_devices. It unambiguously states the tool's purpose as a read operation for a single node.

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 name and description: use this when you need detailed info about a specific node. However, there is no explicit guidance on when not to use it or alternatives (e.g., discover_nodes for discovery, get_cluster_status for cluster-level info). The description does not mention any contextual prerequisites or 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?

There are no annotations, so the description must disclose side effects. It only says 'Initialize' without clarifying whether the operation is destructive, idempotent, requires specific permissions, or what happens if a CA already exists. This is a significant gap 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 description is a single, front-loaded sentence with no filler. It communicates the core purpose efficiently and is appropriately concise for the tool's complexity, though it sacrifices detail for brevity.

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 and no output schema, the description is insufficient. It omits parameter meanings, potential side effects, required permissions, and any guidance on when this should be called relative to other cluster operations.

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 schema has no property descriptions (0% coverage) and the description does not mention parameters at all. Organization, country, and validity_days are not explained, so the description adds no semantic value beyond the parameter names themselves.

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 'Initialize' with a clear resource 'Certificate Authority' and scope 'for the cluster'. It is distinct from all sibling tools, which focus on cluster/node/pod management, so the agent can confidently select this tool for CA setup.

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 is provided on when to use this tool, prerequisites, or how it fits into the cluster lifecycle. It does not mention alternatives or exclusions, leaving the agent without context for deciding when to invoke it.

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 does not disclose pagination behavior, ordering, or that this is a read-only operation. The word 'all' is misleading given the pagination parameters.

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

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

The description is a single concise sentence with no wasted words. It is appropriately front-loaded and easy to parse.

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 too minimal for a tool with pagination parameters and no output schema. It does not explain what is returned, how pagination works, or clarify the 'all' claim. Simple but missing key context.

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 no additional param information 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 'List all K3s clusters' clearly states the verb (list) and resource (K3s clusters). It does not explicitly distinguish from sibling tools like get_cluster_status, but the name and action are 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?

No guidance is provided on when to use this tool vs alternatives. The description only states the action and does not mention context, prerequisites, or 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?

No annotations are provided, so the description carries the full burden. It only states 'list all GPIO devices across all nodes' without disclosing pagination behavior, performance characteristics, permission requirements, or return format. This is insufficient for a listing tool that likely has pagination.

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

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

The description is a single concise sentence with no wasted words. It is front-loaded and directly addresses the core purpose, earning maximum points for succinctness.

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 minimal annotations, the description leaves significant gaps: it doesn't specify what fields are returned, how pagination works, or any potential side effects. This is inadequate for a tool with three parameters and no structured output documentation.

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 only 33% (only node_id has a description). The tool description does not elaborate on limit/offset semantics, and the phrase 'list all' could obscure the existence of pagination parameters. It adds a hint about node_id ('across all nodes') but nothing more.

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 'list' and resource 'GPIO devices', with scope 'across all nodes', clearly distinguishing it from sibling cluster/node provisioning tools. It is unambiguous about the tool's function.

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 is provided on when to use this tool versus alternatives. There are no exclusions, no prerequisites, and no mention of alternative tools for different scenarios.

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 responsibility for behavioral disclosure. It only reveals that the operation is async, which is useful, but it does not mention potential side effects, resource cleanup, required prior states, or how success is communicated.

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

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

The description is a single sentence that front-loads the action and resource, and includes the key note about async behavior. There is no wasted wording, though the extreme brevity limits the informational value.

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 provisioning operation with 5 parameters, no output schema, and no annotations, the description is under-specified. It does not explain how to monitor the async operation, what 'provisioning' entails, dependencies on other tools, or how this interacts with create_cluster or provision_node.

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 schema covers all parameters with basic descriptions, so the baseline is 3. The description adds no parameter-specific context, such as the relationship between master_node_id and worker_node_ids, the role of k3s_config, or how ssh_config is used for authentication.

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 provisions a K3s cluster on Raspberry Pi nodes, which is a specific verb+resource combination. It distinguishes from sibling tools like create_cluster (likely a metadata operation) and provision_node (single node), though it does not explicitly name alternatives.

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 no guidance on when to use this tool versus alternatives like create_cluster or provision_node. It mentions async operation but omits prerequisites, context, or 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 full responsibility for disclosing side effects, prerequisites, and operational details. It only states the action without mentioning SSH requirements, whether the operation is idempotent, what state changes occur, or error conditions.

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

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

The description is a single sentence with no filler, front-loading the core purpose. It is appropriately concise for the simple action it names.

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 tool's complexity (4 parameters, nested ssh_config, worker join tokens), the description is too sparse. It lacks information about return values, prerequisites, and how it relates to cluster provisioning, making it incomplete for safe invocation without additional context.

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, so the schema already documents each parameter. The description adds no additional meaning beyond what is structured, warranting the baseline score of 3.

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

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

The description clearly identifies the tool's action ('Provision K3s') and scope ('single node'), which differentiates it from the sibling provision_cluster for whole clusters. The verb+resource structure is specific and 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?

No guidance is provided on when to use this tool versus alternatives like provision_cluster or register_node. It does not mention prerequisites, exclusions, or typical scenarios, leaving the agent to infer usage context from the 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, the description carries full responsibility for disclosing side effects. 'Register' implies a write operation but does not state whether it validates connectivity, requires an existing cluster, or is idempotent. This significant gap leaves the agent uncertain about consequences.

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

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

The description is a single, clear sentence with no wasted words. It is concise but perhaps overly terse for a tool with five parameters; however, brevity alone does not detract from structural quality.

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 minimal for a tool with five parameters and many siblings. It does not explain what 'register' entails, prerequisites, return behavior, or how it differs from provision_node. This is insufficient context for reliable tool selection and invocation.

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

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

Schema descriptions cover 100% of parameters, including enums for role and architecture, so the baseline is 3. The description itself adds no parameter details beyond the schema, but also doesn't need to since coverage is complete.

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 action ('Manually register') and the resource ('a Raspberry Pi node'), distinguishing it from automatic discovery tools like discover_nodes. However, it doesn't explicitly distinguish from provision_node, which may have overlapping semantics.

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 such as discover_nodes or provision_node. The word 'Manually' implies a contrast to automated discovery, but no explicit exclusions or alternative recommendations 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?

With no annotations, the description carries the full burden of behavioral disclosure. It mentions adding/removing worker nodes, but does not disclose that removing nodes may be destructive, that scaling may be asynchronous, or that SSH configuration is required. The effect on existing workloads is not addressed.

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

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

The description is a single, front-loaded sentence with clear wording and no filler. It conveys the core purpose efficiently, earning a perfect score for 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?

The tool involves a nested ssh_config object and side effects like adding/removing nodes, but the description does not explain SSH requirements, provisioning behavior, or expected outcomes. With no output schema or annotations, important context 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 100%, so the baseline is 3. The schema already defines node_count as 'Desired total number of worker nodes' and cluster_id as required. The description adds minimal semantic value beyond the schema and does not clarify ssh_config usage.

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 ('Scale') with a clear resource ('a cluster') and scopes the operation to 'adding or removing worker nodes'. This distinguishes it from sibling tools like create_cluster and delete_cluster, though it does not explicitly name alternatives.

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 no guidance on when to use this tool versus siblings such as provision_cluster or deprovision_node. The context is implied by the verb 'scale,' but there is no explicit when-to-use, prerequisites, or exclusion criteria.

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