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

With readOnlyHint=false, destructiveHint=false, the description confirms a write operation ('Upload'). However, it adds no additional behavioral context such as idempotency, side effects, or authentication requirements. Annotations are minimal, and the description does not compensate.

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. However, it could be slightly expanded to include useful context without losing 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?

Despite having 4 parameters, nested objects, and an output schema, the description is minimal. It does not explain the attachment payload pattern, response format, or any constraints. More context is needed for an AI agent to use the tool effectively.

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 schema already documents all parameters. The description adds nothing beyond the schema's parameter descriptions. Baseline 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 'Upload evidence to a manual test result' clearly states the action (upload) and the target resource (evidence to manual test result). It distinguishes from sibling tools like 'add_test_step_attachment' by specifying 'test result' rather than 'test step', but lacks explicit differentiation.

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 'add_test_step_attachment' or 'upload_test_results'. There is no mention of prerequisites, when not to use it, or context for selection.

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 this is a write operation (readOnlyHint=false). Description adds that it targets 'manual attachment steps', but doesn't disclose additional behavioral traits like error handling or step resolution logic.

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?

Single sentence, front-loaded with action and target. No unnecessary 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?

Despite high parameter count (10) and complex step resolution logic (step_name, step_index, attachment_id, fixture fallback), the description provides no explanation of how these parameters interact or the expected attachment payload format. Output schema exists but doesn't compensate for missing usage 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 coverage is 100%, so the schema describes all parameters. The description adds no extra meaning beyond the schema's own 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 action ('Upload evidence') and the target ('manual attachment step inside a test result'). It distinguishes from similar tools like 'add_test_result_attachment' by specifying step-level attachment.

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 (e.g., 'add_test_result_attachment'). No mention of prerequisites or when not to use 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?

Annotations already include destructiveHint=true. The description adds context by stating 'reassigning test cases changes their hierarchy location,' which is helpful but not extensive.

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 sentences with no wasted words: first states purpose, second provides a crucial caution. Efficient and front-loaded.

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

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

Given the presence of annotations, full schema coverage, and an output schema, the description is adequate. It covers the destructive nature and the core function, though it could expand on hierarchy implications.

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% coverage with descriptions for all 5 parameters. The description does not add additional semantic meaning beyond what the schema provides, so 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?

Clearly states the action (assign) and resources (test cases to a suite path). Distinguishes itself from sibling tools like create_test_case or manage_test_plan_content by focusing on hierarchical 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 explicit guidance on when to use this tool over alternatives. The caution about destructiveness hints at a downside but does not provide decision criteria or compare with related tools.

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 idempotentHint=true. The description adds that it returns updated launch details, providing extra 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?

The description is a single, concise sentence that is front-loaded with the action and result. No extraneous 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?

Although the tool has an output schema and annotated traits, the description lacks guidance on when to use it among sibling tools. It is 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 coverage is 100%, so the description does not add meaning beyond what the schema already provides. It meets the baseline but does not enhance parameter understanding.

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 'close' and the resource 'launch', and it adds that it returns updated details, distinguishing it from related tools like delete_launch or reopen_launch.

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 delete_launch or reopen_launch. The description is minimal and does not provide context for appropriate usage.

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 it's not read-only or destructive. The description adds no extra behavioral context, such as side effects or authorization needs, so it doesn't add value beyond 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 extremely short (one sentence), which is concise but lacks structure. It could be expanded with a brief sentence about usage context without sacrificing conciseness.

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

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

For a creation tool with 5 parameters and an output schema, the description is too minimal. It doesn't explain the purpose of the custom field value or how to specify the custom field (id vs name). Incomplete for an agent to use confidently.

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 does not add any parameter meaning beyond what the schema already provides (e.g., name, project_id, etc.).

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 the resource 'custom field value option', distinguishing it from sibling tools like update and delete. However, it could be more specific about the context (e.g., 'for a specific custom field').

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 list_custom_field_values or update_custom_field_value. No prerequisites (e.g., need to specify custom_field_id or name) 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?

Annotations indicate a write operation (readOnlyHint=false, destructiveHint=false) align with 'create'. Description adds context about linking to test results but doesn't disclose missing details like duplicate handling or project scope. With annotations present, the description is adequate.

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 sentences front-load the purpose and provide usage context without unnecessary words. Efficient for a tool with few parameters.

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 core responsibility and usage context. With an output schema present, no need to detail return values. Sufficiently complete for a create operation.

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 description adds no new parameter details beyond the schema. The description mentions 'known defect' but doesn't elaborate on parameters like name, description, or output_format.

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 creates a new defect in the current project and explains its purpose for linking to failing test results via defect matchers. It distinguishes from sibling tools like update_defect, list_defects, and create_defect_matcher.

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 a clear usage scenario (registering a defect for future linking) without explicitly stating when not to use or listing alternatives. The context is sufficient given the sibling set.

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 indicate the tool is not read-only, not idempotent, and not destructive. The description adds behavioral context beyond annotations by explaining how matchers work (matching error messages/stack traces) and the requirement for at least one regex, which is a behavioral constraint not captured in the 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 consists of three concise sentences that are front-loaded: first states the main action, second explains the mechanism, and third gives a key constraint. Every sentence adds essential information with no unnecessary 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 the tool's complexity (5 parameters, 2 required, no enums) and the presence of an output schema, the description adequately explains the tool's function and key constraints. It covers the core behavior and the important 'at least one' rule, which is sufficient for an agent to select and invoke the tool 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?

With 100% schema description coverage, the baseline is 3. The description adds value by explicitly stating the business rule that at least one of message_regex or trace_regex must be supplied, and by providing context on how these regex patterns are used (matching error messages or stack traces).

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 the resource 'defect matcher', and explains its purpose as an automation rule that links future failing test results to a defect based on regex patterns. This distinguishes it from siblings like create_defect or update_defect_matcher.

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 for when to use the tool: to set up automatic linking of test failures to a defect. It also explicitly states the constraint that at least one regex must be supplied. However, it does not explicitly mention alternatives or when not to use it, but the naming and sibling list make it 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?

The description does not disclose any behavioral traits beyond the annotation flags (all false). It fails to mention side effects (e.g., whether a new launch affects existing test runs), required permissions, or the impact of optional parameters like `autoclose` or `external`. With no annotations providing additional context, the description leaves the agent underinformed.

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 clearly identifies the action and target, making it easy for an AI agent to quickly grasp the tool's primary function.

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 8 parameters and an output schema, the description is too sparse. It does not explain what a 'launch' represents in Allure TestOps, how it relates to test cases or plans, or how the optional parameters affect behavior. The agent lacks context to use the tool effectively alongside the many sibling tools.

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

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

The input schema provides descriptions for all 8 parameters (100% coverage), so the description does not need to repeat them. However, the description adds no extra meaning beyond the schema, such as clarifying the relationship between parameters (e.g., how `tags`, `links`, and `issues` interact). A score of 3 is appropriate as the schema does the heavy lifting.

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 ('Create') and the resource ('a new launch'), and specifies the system ('Allure TestOps'). It effectively distinguishes this tool from siblings like `delete_launch`, `close_launch`, and `reopen_launch` by indicating its purpose as creation.

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 (e.g., `upload_test_results` or `submit_manual_test_results`). It lacks any 'when-to-use' or 'when-not-to-use' context, and does not mention prerequisites or common 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?

The description adds no behavioral context beyond what annotations already provide (readOnlyHint=false indicates creation). It does not disclose side effects, permissions, or output format, which is important for a creation 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 sentence, but it is too terse for a tool with 4 parameters and a complex nested structure. Conciseness is achieved at the cost of completeness.

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 presence of an output schema and complex parameters, the description fails to provide sufficient context about the tool's role in test management or how it relates to siblings like link_shared_step. An agent would lack essential selection cues.

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 with detailed explanations for each parameter. The description adds no additional meaning, so 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 clearly states the action ('Create') and resource ('reusable Shared Step'). It is specific but does not differentiate from siblings like update_shared_step or delete_shared_step beyond the verb.

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 (e.g., searching or updating shared steps). The description provides no context for selection among siblings.

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?

Description adds no behavioral context beyond annotations. Annotations indicate readOnly=false, but no details on permissions, idempotency, or side effects. Description does not disclose any traits.

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?

Single sentence, efficiently front-loaded with verb and resource. However, could be slightly more informative given tool complexity, but still concise.

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 13 parameters and availability of output schema, description covers only basic purpose. Lacks context on return value or action outcome, but output schema presumably covers return. Adequate but minimal.

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% coverage, so baseline is 3. Description does not add semantic information for parameters beyond what 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?

Description uses specific verb 'Create' and resource 'test case' with location 'Allure TestOps'. It clearly distinguishes from sibling tools for other operations (e.g., update, delete) and other entities (e.g., defects, test suites).

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 vs alternatives. Does not mention prerequisites, context, or exclusions despite many sibling tools.

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?

Minimal behavioral disclosure beyond creating a layer. Annotations are non-informative (no readOnly, idempotent, or destructive hints). Description does not state side effects, required permissions, or whether the layer is immediately usable. Context beyond schema is lacking.

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 concise sentences with no fluff. First sentence states the action clearly; second provides context about what test layers are. Information is front-loaded and easy to scan.

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?

Adquately covers purpose and one parameter hint, but lacks details on when project_id is needed and output_format effects. Output schema exists, so return values are not required. Overall minimal but meets basic needs.

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 100% of parameters with descriptions. The description reinforces the name parameter with examples but adds no additional meaning to project_id or output_format. Since schema already explains, description adds marginal value.

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 tool creates a test layer, defines what test layers are (taxonomy for categorizing test cases), and provides concrete examples ('Unit', 'Integration'). Distinguishes from sibling tools like update_test_layer and delete_test_layer by focusing on creation.

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 explicit guidance on when to use this tool versus alternatives. Does not mention prerequisites (e.g., requires a project) or when not to use it. Implied usage only from the purpose.

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 indicate the tool is not read-only, idempotent, or destructive. The description adds no further behavioral details (e.g., error handling, permissions, conflicts). With annotations present, the bar is lower, but description could still be more informative.

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 concise: two paragraphs sum up the purpose and function without redundancy. Every sentence contributes to understanding.

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, no nested objects, existence of output schema), the description adequately explains the concept of test layer schemas and their role. It provides sufficient context for an agent to decide to use this 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 description coverage is 100%, so the schema already documents all parameters. The description repeats the general concept (mapping key to layer) but does not add specific parameter-level semantics beyond what the schema 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 states the tool creates a new test layer schema that maps a custom field key to a test layer. It distinguishes from sibling tools like create_test_layer (which creates layers) and other schema tools (list, update, delete) by focusing on the creation of mappings.

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 explains that schemas allow automatic assignment of test cases to layers based on custom fields, giving context for when to use this tool. However, it lacks explicit statements about when not to use it or alternatives (e.g., if schema already exists).

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 indicate readOnlyHint=false and destructiveHint=false, which are consistent with creating a non-destructive entity. The description adds behavioral context by explaining that the tool can create a plan using explicit IDs, an AQL filter, or both. This goes beyond the annotations without contradiction.

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 primary action and resource. It efficiently covers purpose and methods without unnecessary 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 the tool's simplicity and the existence of an output schema, the description provides sufficient context: it identifies required parameter (name), explains optional parameters, and outlines the two content selection strategies. No gaps remain.

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 value by explaining the dual approaches (test_case_ids and aql_filter) and their combined use, enhancing understanding beyond the schema. Output_format is well-described in the schema.

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

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

The description clearly states the verb 'Create' and the resource 'Test Plan in Allure TestOps'. It differentiates from siblings like 'manage_test_plan_content' and 'update_test_plan' by focusing on creation, and explains the two primary methods for defining content (test_case_ids and aql_filter).

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 explains when to use the tool (to create a new test plan) and outlines the two content selection methods. It does not explicitly state when not to use it or name alternatives, but the context implies it is for creation only, which is clear from the purpose.

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 readOnlyHint=false and destructiveHint=false, so the description does not need to restate. However, it adds the context of a hierarchy tree, which is helpful. But it doesn't disclose any additional behavioral traits like idempotency, handling of duplicate names, 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?

A single, clear sentence with no extraneous words. It is concise and front-loaded. However, it could be slightly more informative without losing 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?

Given the tool has 5 parameters (1 required) and an output schema exists, the description is minimally adequate. It states the purpose but does not explain the hierarchy concept, return value, or error conditions. With an output schema, the agent can infer return format, but more context would help.

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 input schema already describes all parameters. The description does not add any extra meaning beyond what is in the schema. 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?

Description clearly states the action ('Create'), the resource ('new test suite node'), and the context ('in the hierarchy tree'). It effectively distinguishes from sibling tools like list_test_suites and delete_test_suite.

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 (e.g., create_test_case, manage_test_plan_content). No exclusions or prerequisites mentioned. The description is purely functional without usage 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?

Annotations already indicate destructiveHint=true and readOnlyHint=false, so the description's 'permanently delete' aligns. However, it does not elaborate on idempotency (idempotentHint=true) or other behavioral traits like potential data loss, so it adds limited value beyond 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 a single, well-structured sentence with no wasted words, front-loading the action and resource for quick understanding.

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 full schema coverage and an output schema, the description covers the core intent. It could mention the confirm parameter requirement for destructive operations, but overall it provides sufficient context for a bulk deletion 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 description coverage is 100%, so the schema already documents all parameters. The description does not add extra meaning beyond what the schema provides, meeting the baseline for high coverage.

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 (permanently delete), the resource (archived shared steps), and the scope (all in current project). This distinguishes it from sibling tools like delete_shared_step (which deletes a single step) and delete_archived_test_cases.

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 (e.g., delete_shared_step for individual deletion), nor does it mention prerequisites or contexts where it should not be used.

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. The description adds context by specifying the permanence and scope ('permanently delete all archived/deleted test cases'). It does not contradict annotations. However, it could warn about the lack of recovery or mention that the confirm parameter safeguards the action.

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-structured sentence that front-loads the core action. No unnecessary words or information, making it highly concise.

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 destructive bulk action, annotations (destructiveHint), input schema, and presence of an output schema, the description covers the essential behavioral and usage context. No gaps are apparent for this tool's complexity.

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

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

Schema coverage is 100%, and the description adds no additional explanation for parameters. The schema already defines confirm, project_id, and output_format with descriptions. Baseline 3 is appropriate as the description does not enrich parameter understanding.

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 permanently deletes all archived/deleted test cases within the current project. It uses a specific verb ('delete') and resource, distinguishing it from siblings like delete_test_case (single) or delete_archived_shared_steps.

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. It does not mention that this is for bulk cleanup of archived items, nor does it exclude scenarios where delete_test_case is more appropriate. Sibling tools exist for single deletion, but no comparison is given.

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 provide destructiveHint=true and idempotentHint=true. The description adds a caution emoji but does not elaborate on behavior such as error handling, deletion consequences, or idempotency effects. It adds minimal beyond 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 very short (one sentence plus a caution line) and front-loaded. For a simple delete operation, this conciseness is appropriate, though it could include more context without becoming verbose.

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

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

Given the 6 parameters and existence of output schema, the description is minimal. It does not explain post-deletion behavior or potential side effects. However, annotations cover the destructive nature, so it is moderately complete for a simple 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% with detailed parameter descriptions. The tool description does not add any additional semantic information about parameters beyond what is already in the schema, so baseline score of 3 applies.

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

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

The description uses a specific verb-resource pair 'Delete a custom field value,' clearly identifying the action and object. Among sibling tools, it is distinct from create/update/list operations for custom field values.

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 (e.g., delete_unused_custom_fields or other delete tools). The description only states the action and a caution, lacking context for appropriate usage 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?

Annotations already indicate destructiveHint=true, and the description adds useful context: the operation is permanent and affects both the defect and associated matchers. There is no contradiction with annotations. The description does not cover all behavioral nuances (e.g., error handling), but it provides meaningful additional information.

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 exceptionally concise at two sentences, with no wasted words. It front-loads the core action and immediately follows with the critical usage condition, making it efficient for an agent 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?

Given the low tool complexity and comprehensive schema and annotations, the description is largely complete. It covers the destructive nature and the required confirmation flag. The presence of an output schema alleviates the need to explain return values, but a brief note on prerequisites or error cases would be beneficial.

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 baseline is 3. The description emphasizes the importance of the 'confirm' parameter, which is already documented in the schema, but does not add new meaning for the other parameters ('defect_id' and 'output_format').

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: permanently delete a defect and all its associated matchers. This is a specific verb+resource combination that distinguishes it from siblings like 'delete_defect_matcher' (only deletes a single matcher) and 'update_defect' (modifies instead of deletes).

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 guidance on the required condition: the 'confirm' parameter must be set to 'true' to actually perform the deletion. However, it does not explicitly mention when not to use this tool or suggest alternatives.

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 idempotentHint=true. The description adds clarity by explicitly stating it is destructive and explaining the confirm parameter as a safety net, which goes beyond the hints.

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 concise sentences front-loaded with the action and then the safety requirement. 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?

For a delete tool with annotations and output schema, the description covers the basic usage and safety flag. However, it omits what happens if the matcher_id is invalid or if confirm is false (e.g., error vs no-op), which could be important for an agent.

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 schema already documents each parameter. The description only mentions the confirm parameter, adding no new information beyond what is in the schema.

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

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

The description clearly states the action (permanently delete) and the resource (defect matcher). It distinguishes itself from sibling tools like create_defect_matcher, update_defect_matcher, and list_defect_matchers, and other deletion tools.

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 the destructive nature and the need to set 'confirm' to true, but it does not provide guidance on when to use this tool versus alternatives (e.g., disabling via update_defect_matcher) or any 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?

The description adds a caution about destructiveness, but annotations already declare destructiveHint=true. It does not disclose idempotency, return values, or consequences beyond what annotations provide. Minimal added value.

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 one sentence with a caution symbol, very concise with no wasted words. However, it could be structured to highlight key points like idempotency or parameter hints.

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 does not mention return values (though output schema exists), optional parameters like project_id and output_format, or side effects beyond destructiveness. For a destructive tool with optional parameters, more context would be beneficial.

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 describes all 3 parameters with 100% coverage. The description does not mention any parameters or add meaning beyond the schema, so 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 'Delete a launch by ID', using a specific verb and resource. This distinguishes it from sibling tools like close_launch or delete_test_case.

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, prerequisites, or whether to close the launch first. The description is silent on usage 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?

Annotations already indicate destructiveness, but the description adds specific warnings about breaking references in test cases. This provides valuable behavioral context beyond what annotations convey, without contradiction.

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 extremely concise with two sentences and two caution notices. It is front-loaded with purpose and wastes no 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 the presence of an output schema and full parameter descriptions, the description sufficiently covers purpose and key side effects. It is complete for the tool's complexity.

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 description does not need to add parameter details. It does not provide additional meaning beyond the schema, earning 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 verb 'Delete', the resource 'shared step', and the location 'library'. It distinguishes the tool from siblings like 'delete_test_case' and 'delete_archived_shared_steps'.

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 context for when to use (to delete a shared step) but lacks explicit guidance on when not to use it or alternatives. The caution about breaking references implies careful usage but no direct comparison to other tools.

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?

Discloses soft delete nature and recovery option, adding context beyond destructive annotation. 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?

Concise with front-loaded action, though caution messages are slightly repetitive; overall efficient.

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

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

With output schema present, description adequately covers behavior and side effects; could mention idempotency hinted by annotation.

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 with descriptions; description adds no additional parameter-specific meaning, meeting baseline for 100% coverage.

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 tool archives an obsolete test case via soft delete, distinguishing it from siblings like delete_archived_test_cases.

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?

Describes when to use (obsolete test cases) and effects on historical data, but lacks explicit comparison to alternatives like delete_archived_test_cases.

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, so the caution emoji and 'Destructive' are redundant. The description does not mention the required confirm parameter or other behavioral traits like permanent deletion or cascading effects, which are not covered by 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 extremely short (one sentence) but omits critical details like the confirm parameter requirement. It is concise but under-informative.

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

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

Given the tool has 4 parameters, an output schema, and required confirmation, the description fails to mention the need to set confirm=true or the effect of output_format. It is not complete enough for safe usage.

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% (all 4 parameters have descriptions). The tool description adds no additional parameter details beyond what the schema provides, scoring baseline 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 'Delete a test layer from Allure TestOps' uses a specific verb ('Delete') and resource ('test layer'), clearly distinguishing it from siblings like create_test_layer, update_test_layer, and list_test_layers.

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 (e.g., delete_test_case, delete_test_layer_schema) or any prerequisites. The description only states the action without contextual usage advice.

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?

Caution about destructiveness adds no value beyond the already present destructiveHint annotation. No disclosure of side effects (e.g., cascade delete, permissions) or required confirmation steps.

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 sentences with clear purpose and warning. Front-loaded but could be slightly more informative without adding length.

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 destructive tool, missing context about the confirm parameter (important for safety) and what happens after deletion. Output schema exists but not referenced.

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 baseline is 3. Description adds no extra meaning to parameters like confirm, project_id, or output_format.

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 'Delete' and resource 'test layer schema' directly state the action. Distinguishes from sibling tools that operate on different entities (test cases, test layers, etc.).

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

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

No guidance on when to use this tool versus alternative actions like update or list. Lack of context on prerequisites or when deletion is appropriate.

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 provide destructiveHint=true and idempotentHint=true. The description adds context by stating 'Permanently removes' and explaining idempotent behavior ('if the plan does not exist, it returns success'), enhancing transparency beyond 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-loaded with the action, uses a caution emoji for emphasis, and contains no unnecessary words. Every sentence adds 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 simple deletion tool with a safety confirm parameter, the description covers core behavior, permanence, and idempotency. It does not mention permissions or cascading effects, but given the tool's simplicity and presence of an output schema, it is mostly 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?

Schema coverage is 100% with all three parameters described. The description does not add parameter-specific information beyond the schema; e.g., it doesn't mention the confirm safety flag. Baseline 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 'Delete a Test Plan' with the verb 'Delete' and resource 'Test Plan'. It further clarifies with 'Permanently removes the Test Plan from Allure TestOps', distinguishing it from sibling tools like delete_test_case or delete_launch.

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 a caution about destructiveness and mentions idempotency, but does not explicitly state when to use this tool versus alternatives (e.g., manage_test_plan_content, update_test_plan) or when not to use 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?

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description reinforces this with an explicit CAUTION warning. It adds the useful caveat that nested entities are handled according to Allure TestOps's tree-group API behavior, though it stops short of explaining exactly what happens to those nested items. No contradiction with the annotations exists.

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 short and front-loaded: the core action and a danger warning appear in the first two lines, followed by the nested-entity caveat. There is no filler or repetition, though the final sentence is somewhat vague and could be more specific without hurting 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?

Given a destructive tool with detailed per-parameter schema descriptions and an output schema, the description is reasonably complete: it states what is removed, warns about destructiveness, and flags nested-entity behavior. It does not need to repeat the confirm flag or output format details already in the schema. The main gap is the unspecified effect on child nodes, but the API-behavior caveat at least acknowledges this nuance.

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 schema fully documents all five parameters, including the confirm safety measure and optional tree_id/project_id. The description adds only a slight reinforcement that suite_id targets a suite/group node, but does not need to explain parameter semantics further. Baseline 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 opens with a specific verb and resource: 'Delete a test suite node from hierarchy.' It further defines the target as a 'suite/group node,' which distinguishes it clearly from sibling deletion tools like delete_test_case, delete_test_plan, and delete_launch. The purpose is immediately identifiable 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?

The description establishes clear context: this tool is for removing hierarchy suite/group nodes, so it is appropriate when deleting a test suite node rather than a test case, plan, launch, or shared step. It does not explicitly name alternatives or when-not conditions, but the resource scoping is sufficient for correct routing in most cases.

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 (destructiveHint=true, idempotentHint=true), description adds the specific 'unused' condition and scope 'in the current project'. No contradictions.

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?

Single, clear sentence. No waste, front-loaded.

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

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

Tool has output schema, so return values are covered. Description covers purpose, condition, and scope. Complete for this use case.

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 description adds little beyond schema's parameter descriptions. Description does not elaborate on confirm or output_format beyond 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?

Description clearly states the action (delete), resource (custom fields), and condition (unused by any test case). It distinguishes from sibling tools like delete_custom_field_value or delete_test_case.

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?

Implies usage for removing orphaned custom fields but lacks explicit when-to-use or when-not-to-use guidance, and does not mention alternatives like get_custom_fields or delete_custom_field_value.

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 readOnlyHint=true and destructiveHint=false, so the description's value is limited. It adds that validation is performed locally and only requested metadata is synchronized, which provides useful but not critical behavioral context beyond 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 concise with two sentences, front-loading the main action. It efficiently communicates purpose and key requirements without unnecessary verbiage.

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 five parameters including enums and an output schema, the description covers the core concept but lacks details on the generated output format, error cases, or specific behavior for edge cases. It is adequate but leaves room for more 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 schema already documents all parameters. The description adds minimal extra meaning (e.g., 'Both target selections are required') but does not significantly enhance understanding 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?

Description clearly states the verb 'Generate' and the resource 'test snippet from a TestOps test case', making the tool's primary function immediately obvious. It distinguishes itself from sibling tools like create_test_case or get_test_case_details by focusing on code generation.

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 that both target selections (language and framework) are required, giving some usage context. However, it does not explicitly state when to use this tool vs alternatives, nor does it provide scenarios where it would not be appropriate.

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 provide readOnlyHint, idempotentHint, and destructiveHint, so the description's job is lighter. It adds that the tool returns 'allowed values,' which is not in annotations or schema. However, it does not disclose other behavioral traits like data source or limitations. This is adequate but not exceptional.

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 concise sentences. The first states the core purpose, and the second provides usage guidance. Every sentence adds value, with no redundancy or fluff.

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 presence of an output schema and annotations, the description provides sufficient context for the agent: it explains the tool's role in the workflow (discovery before creation/update) and its input/output nature. No critical gaps exist for the tool's simplicity.

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 covers all 3 parameters with full descriptions, achieving 100% coverage. The description does not add new parameter semantics beyond what is in the schema. According to rules, baseline is 3 when coverage is high, and no extra value 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 retrieves available custom fields and their allowed values for a project. It uses specific verbs and resources ('Get available custom fields') and differentiates itself from sibling tools like list_custom_field_values and create_custom_field_value by emphasizing it is used to discover fields before creating or updating test cases.

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 explicitly states when to use the tool: 'Use this tool to discover what custom fields are available... essential before creating or updating test cases.' This provides clear context and implies when not to use it (when not needing discovery). It also hints at the prerequisite nature for other operations.

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 readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description simply says 'retrieve', which is consistent but adds no extra 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?

The description is a single concise sentence that states the action and resource. It is front-loaded and efficient, though slightly brief.

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

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

For a simple read operation with an output schema present, the description is adequate. However, it lacks usage guidance and could mention output_format options, but the schema compensates.

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 both parameters are documented in the schema. The description adds no additional meaning beyond what the schema 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?

Description uses specific verb 'retrieve' and resource 'defect', clearly indicating a read operation for a single defect. It distinguishes from siblings like list_defects (listing) and create_defect (creation).

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 does not explicitly state when to use this tool versus alternatives like list_defects. Usage is implied by the name and schema but lacks explicit 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the agent knows this is a safe read. The description adds minimal behavioral context beyond that, mainly the 'summarize' aspect, but does not meaningfully expand on what the agent should expect.

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 operation efficiently enough for a simple get-by-ID 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?

Despite the vague 'summarize' wording, the tool is adequately contextualized for a read-only retrieval: annotations cover safety, the schema covers all parameters, and an output schema exists. The main missing piece is usage guidance relative to sibling launch tools, but that is already penalized in usage_guidelines.

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 parameters are already documented. The description adds little beyond implying that launch_id identifies the specific launch to retrieve, which is already clear from the schema.

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

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

The description states a clear verb+resource: retrieving a specific launch. The use of 'specific' slightly differentiates it from list_launches, but it does not explicitly name or contrast any sibling tool, and 'summarize its details' is somewhat vague.

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 versus alternatives such as list_launches or get_launch_test_results. The only implicit cue is 'specific launch', but no explicit context, prerequisites, or exclusions 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?

Annotations already declare readOnlyHint and idempotentHint as true. The description adds useful behavioral details like case-insensitive matching and partial match acceptance, which go beyond 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 concise with two sentences, covering all necessary aspects without verbosity. It effectively prioritizes key information.

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

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

For a read-only tool with an output schema, the description is complete. It covers both usage modes (single project retrieval and listing) and provides sufficient context for an agent to use the tool effectively.

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 value by explaining the name parameter's matching behavior (case-insensitive, partial match) and clarifying the output format default ('json' instead of null). This provides extra context 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 clearly states that the tool retrieves a specific project by name or lists all accessible projects. This distinguishes it from sibling tools like create_test_case or get_test_case_details, 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?

Description explains when to omit the name parameter (to discover project IDs) and details name matching behavior (case-insensitive, exact match preferred). However, it does not explicitly mention when not to use this tool or provide alternatives, but context makes it clear as a read-only 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds minimal behavioral detail beyond what annotations imply (retrieve operation). No contradiction, but no extra context about error behavior or side effects.

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 (8 words). It is front-loaded but could include a brief note about optional parameters or output format. However, it is not wasteful and fits a simple read 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?

Given the presence of output schema, full schema coverage, and annotations, the description is minimally adequate. However, it lacks context about when to use this tool vs. similar custom field tools, which would improve completeness for an AI agent.

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 descriptions for all parameters. The description does not add any additional meaning beyond what the schema already provides. Baseline 3 is appropriate since the schema handles parameter documentation.

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 (retrieve), the resource (custom field values), and the scope (for a specific test case). This differentiates it from sibling tools like get_custom_fields (which retrieves definitions) or list_custom_field_values (which may list all values).

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. There are many sibling tools related to custom fields (e.g., list_custom_field_values, create_custom_field_value), but no explicit context or exclusions are given.

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 cover the read-only, idempotent, and non-destructive nature. The description adds valuable behavioral context beyond annotations: attachments are not directly returned but require a separate prepare_attachment_download call followed by an HTTP GET to a Lucius URL. This is important for correct usage.

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 concise and front-loaded with the core purpose. The attachment workflow sentence earns its place. The opening sentence is slightly redundant with the title, but overall the structure is clear and efficient.

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

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

With an output schema present, full parameter schema coverage, and annotations describing the safety profile, the description covers the essential behavior, attachment handling workflow, and a relevant use case. Nothing critical is missing for an agent to invoke this tool 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 schema already documents all three parameters. The description does not add much parameter-level detail beyond clarifying that test_case_id is also needed in the attachment download workflow. This meets the baseline but does not exceed it.

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 retrieves complete details of a specific test case, listing the included components (steps, tags, custom fields, attachments). This distinguishes it from sibling tools like list_test_cases, get_test_case_custom_fields, and prepare_attachment_download.

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 explicitly says to use this before updating a test case to understand its current state, and it gives a concrete follow-up workflow for downloading attachments. It provides clear context but does not explicitly state when not to use it or compare it to alternatives.

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 meaningful context beyond that: the result is non-recursive, attachment references identify their verified owner, and downloads require calling prepare_attachment_download and using the returned Lucius URL before expiry. This is valuable behavioral disclosure.

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 compact and front-loaded with the core purpose. The second sentence adds an actionable attachment workflow that is directly relevant. No filler is present, though the second sentence is dense.

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 annotations, full schema coverage, and output schema, the description covers the essential behavior, scope exclusion, and attachment handling without missing anything needed for correct invocation. The tool is simple and the description completes it.

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

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

Schema description coverage is 100%, and the schema already explains test_result_id, project_id, and output_format precisely. The description adds no additional parameter-level meaning, so the 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 states a specific verb ('Retrieve') and a specific resource ('one complete TestOps result'), and adds an explicit scope limitation ('without recursively reading related results'). This distinguishes it from sibling list/search tools and makes the tool's purpose immediately clear.

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 first sentence gives clear context for when to use this tool: retrieving a single complete result, not recursively related results. The attachment guidance also routes the agent to prepare_attachment_download when needed, though it does not explicitly name alternatives for retrieving multiple results.

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 readOnlyHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds useful behavioral context by clarifying that this is a targeted, non-recursive read and that it only returns directly assigned test cases, which is beyond what the annotations or schema alone convey.

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 two short sentences with no wasted words. The core purpose is front-loaded, and the second sentence adds only the scoping details needed to avoid misuse with broader read tools.

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

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

For a simple, read-only, idempotent tool, the description combined with the fully described schema and existing output schema is complete. The agent has everything needed to call it correctly: required parameter, optional parameters, output format, and behavioral boundaries.

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 schema fully documents all five parameters. The description does not add meaning about parameters beyond what the input schema already provides; therefore the 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 opens with a specific verb and resource: 'Get test cases directly assigned to one test suite.' It distinguishes itself from broader enumeration and recursive traversal by calling itself a 'targeted hierarchy read,' which differentiates it from sibling tools like list_test_cases and list_test_suites.

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 when to use it: when the agent needs only test cases directly assigned to a single suite. It also states exclusions—does not enumerate unrelated suites or recursively traverse the project tree—but it does not explicitly name an alternative tool for recursive traversal, so it falls just short of 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 provide idempotentHint=true and destructiveHint=false. Description confirms linking but does not add extra behavioral details (e.g., permissions, scope, 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?

Two concise sentences, no redundant words. Could be slightly more structured, but overall efficient.

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

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

With output schema present and full parameter coverage, the description is adequate. It explains the connection between defect and test case, but could mention prerequisites like integration setup.

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 handles parameter meaning. Description does not add new semantics beyond what is already in the property 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?

Clearly states the action ('link a defect to a test case') and the mechanism ('shared issue mapping'), distinguishing it from siblings like 'unlink_issue_from_test_case'.

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 (e.g., 'unlink_issue_from_test_case'). The description only mentions benefits but no when-not-to-use or alternative 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?

The description claims 'CAUTION: Destructive' but annotations set destructiveHint to false, creating a contradiction. This undermines trust; the description should align with annotations. Additionally, it provides some context about shared step expansion at execution time, but the contradiction is severe.

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 concise with three sentences: a clear purpose statement, a warning emoji, and a brief explanation of behavior. No unnecessary information; each sentence adds 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?

Given the tool has 6 parameters, an output schema, and annotations, the description covers the basic function and a warning, but it does not explain how parameters interact or what to expect in the output. The contradiction with annotations further reduces completeness. The output schema is present but the description doesn't leverage it.

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

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

Schema description coverage is 100%, so the schema fully documents all 6 parameters. The description adds no additional meaning beyond the schema (e.g., does not clarify 'confirm' requirement or 'position' behavior). 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 clearly states the verb 'Link' and the resource 'a shared step to a test case', defining a specific action. It distinguishes from sibling tools like 'unlink_shared_step' by indicating the opposite operation.

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 by explaining the function and adding a caution flag, but it does not provide explicit guidance on when to use this tool versus alternatives (e.g., when not to use it, prerequisites, or scenarios to avoid). There is no mention of when linking is appropriate or if there are constraints.

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 readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the tool's safety profile is clear. The description does not add behavioral context beyond these annotations, but also does not contradict them. It mentions listing but not pagination or filtering specifics, which are covered by the 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 a single, concise sentence with no wasted words. It is front-loaded and directly states the purpose.

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

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

With an output schema present and full schema coverage, the description is minimally viable but could provide more context about pagination, filtering, or the typical return format. It does not explain the nature of 'available values' further.

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 schema already documents all 10 parameters with descriptions. The tool description adds no additional parameter-level meaning, meeting the baseline for high coverage.

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 (available values for a custom field). It effectively distinguishes itself from sibling tools like get_custom_fields which list fields themselves, and create/update/delete custom field values.

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, such as when to list values versus create or update them. No context about prerequisites or typical use cases is given.

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 readOnlyHint, idempotentHint, destructiveHint. Description adds that it lists 'all matchers' but does not disclose pagination, sorting, error handling, or other behaviors beyond 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?

One concise sentence that front-loads the purpose. Could be slightly more structured (e.g., mentioning output), but it earns its place with 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?

For a simple list tool with output schema and clear annotations, the description is fairly complete. It explains the domain (automation rules) but lacks mention of potential error conditions or pagination 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 coverage is 100% with descriptions for both parameters. Description adds context by defining matchers as 'automation rules', but adds no further meaning to the parameters 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?

Description uses specific verb 'List' and resource 'matchers (automation rules)' for a given defect, clearly distinguishing from sibling tools like create/update/delete_defect_matcher.

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 explicit guidance on when to use versus alternatives (e.g., list_defects or other list tools). Usage is implied by the name and parent defect requirement, but lacks exclusions 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?

Annotations already provide readOnlyHint, idempotentHint, destructiveHint. Description adds no further behavioral context (e.g., pagination, sorting, filtering). No contradiction.

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?

One sentence, front-loaded with key information. Could include brief mention of output details but remains concise.

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