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

With no annotations, the description carries the full burden of behavioral disclosure, but it only says 'Add attachment.' It does not mention that this is a write operation, what side effects occur, whether authentication or permissions are needed, or any constraints around attachment content or size.

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, but it earns no place because it merely repeats the tool name. This is under-specification rather than concise helpful writing.

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 two-parameter tool with no output schema, the description and even the schema leave critical gaps: the body is only described as 'Request body (JSON object)' with generic object items, and there is no indication of required attachment payload structure or how the endpoint behaves. An agent cannot confidently invoke this tool correctly from this definition.

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 issueIdOrKey and body. The description adds no parameter meaning beyond what the schema provides, which keeps this at the baseline.

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 'Add attachment' restates the tool name almost verbatim and adds no scope. It names a verb and resource, so it minimally separates add_attachment from get_attachment, but it does not clarify what kind of attachment, where it is added, or how it is supplied.

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 given about when to use this tool versus alternatives such as add_comment, add_worklog, or get_attachment. There are no exclusions, prerequisites, or context signals to help an agent choose it correctly.

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

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

No annotations are supplied, so the description carries the full burden of behavioral disclosureand two words carry none of it. It never mentions that this is a mutating operation on an issue, whether it is reversible, whether permissions are required, or what the response looks like.

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 words is underspecification, not conciseness. There is no front-loaded key constraint and no explanatory structure; every useful fact an agent needs is absent.

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 mutating tool with a nested request object, required issueIdOrKey, no output schema, and many comment-related siblings, this description is severely incomplete. It omits the target resource, behavior, and response information entirely.

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 even though the description adds nothing about parameters. However, the body parameter's schema is misleading for a request object—it lists response-style fields like id, author, created, and self—and its description 'Request body (JSON object)' is unhelpful; the tool description does nothing to clarify the expected payload.

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 'Add comment' restates the tool name with no additional information. It supplies a verb and resource but never names the target (an issue), and nothing distinguishes it from siblings like update_comment, delete_comment, or get_comments.

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 at all. The description gives no context for when to choose add_comment over update_comment, delete_comment, or get_comments, and states no conditions 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?

There are no annotations, so the description must carry the behavioral disclosure burden. 'Add vote' reveals only the basic action and adds no information about permissions, reversibility, idempotency, side effects, or response behavior.

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 terse, but it is under-specified rather than helpfully concise. It restates the tool name and offers no structured information that would help an agent invoke or select the tool correctly.

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

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

For a mutation tool with no annotations and no output schema, this description is not complete enough. It omits the target resource, the expected effect beyond 'vote', and any relationship to related vote/watcher tools, so an agent cannot confidently understand the tool's full behavior.

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

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

Schema description coverage is 100% and the parameter issueIdOrKey is already described as 'The ID or key of the issue.' The description adds no additional parameter semantics, which is acceptable given full schema 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 'Add vote' is essentially the tool name repeated, so it provides no independent clarification of what the tool does. It does not explicitly state that a vote is added to an issue, even though the only parameter is issueIdOrKey.

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 given about when to use add_vote versus the related siblings remove_vote or get_votes. The description does not mention whether the vote is for the current user, whether prior votes matter, or any condition that would favor this tool.

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

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

There are no annotations, so the description carries the full burden of behavioral disclosure. It only states the core action and says nothing about permission requirements, duplicate watcher handling, whether existing watchers are overwritten, or what happens on failure.

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, but this is under-specification rather than effective conciseness. It provides no contextual structure or front-loaded details that help the agent understand the operation.

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 mutating tool with no annotations and no output schema, the description should clarify scope, effects, and usage context. 'Add watcher' is not sufficient for an agent to confidently invoke the tool, especially given the large set of sibling tools.

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

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

Schema description coverage is 100%, with both 'body' and 'issueIdOrKey' already documented. The description itself adds no parameter meaning beyond what the schema provides, 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 'Add watcher' is a near-verbatim restatement of the tool name 'add_watcher', making it essentially tautological. It identifies the general action and resource but does not specify the target (e.g., an issue) or differentiate itself meaningfully from related tools beyond the obvious.

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 usage guidance is provided. The description does not state when to use this tool instead of remove_watcher, get_issue_watchers, or add_vote, nor does it mention any prerequisites or conditions.

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

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

With no annotations provided, the description carries full responsibility for behavioral disclosure. It states no side effects, permissions, notification behavior, estimate-adjustment implications, or response semantics. The only behavioral signal is the verb 'Add', which is already obvious from the tool name.

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, but this is under-specification rather than effective conciseness. Every other dimension suffers from the absence of detail, and the two-word description does not earn its place by conveying any useful information beyond the tool name.

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

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

For a tool with 8 parameters, a nested body object, no annotations, no output schema, and many closely related siblings, this description is completely inadequate. An agent cannot determine the required body format, the meaning of worklog fields, or how the operation affects the issue's time estimate from this definition.

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 even though the description adds no parameter information. The schema provides descriptions for most top-level parameters, though some are truncated and the nested 'body' object's fields lack individual descriptions. The tool description itself adds no semantic value 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 'Add worklog' simply restates the tool name 'add_worklog' without explaining what a worklog is, what it records, or how it relates to an issue. It is a tautology rather than a meaningful definition, and it provides no distinction from sibling worklog tools like update_worklog or get_issue_worklog.

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 add_comment, update_worklog, or get_issue_worklog. There is no mention of prerequisites, required issue context, or typical use cases, leaving the agent to infer entirely from the tool name and schema.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description only repeats the tool name and fails to explain what the operation does, whether it replaces the current assignee, what permissions are required, or what the response contains.

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

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

The description is extremely short but this is under-specification rather than efficient conciseness. Two words cannot provide the information an agent needs to invoke the tool correctly.

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

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

With no annotations, no output schema, and a nested body object, the definition needs meaningful behavioral and contextual detail. The description is completely inadequate: it omits what assigning means, what the response looks like, and how the body object should be populated.

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%, with both parameters described in the schema: issueIdOrKey identifies the issue and body holds the user object. The tool description itself adds nothing about the parameters, but the schema already documents them sufficiently, so the baseline 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 'Assign issue' is a tautology that simply restates the tool name. It gives no detail about what assignment means (e.g., setting an assignee on an issue) and does nothing to distinguish this tool from its many issue-related siblings.

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 about when to use this tool versus alternatives such as edit_issue or do_transition. There is no mention of prerequisites, typical use cases, or exclusions.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Fetch' weakly implies a read-only operation, but the description does not mention response format, error behavior, handling of missing issues, rate limits, or any other important runtime behavior.

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, but this is under-specification rather than effective conciseness. It provides no additional structure or useful detail beyond what the tool name already communicates.

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

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

The tool has a nested body schema, optional controls, no output schema, and no annotations, so the description should provide more operational context. It neither explains return values nor clarifies the purpose of the optional parameters, leaving an agent to infer too much from the schema alone.

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 reported as 100%, so the baseline is 3. The description itself adds no parameter detail, though the body description does say the object contains information about which issues and fields to fetch. Optional parameters like expand, fields, properties, and fieldsByKeys remain semantically unexplained.

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 and resource ('fetch issues'), and 'bulk' weakly distinguishes it from single-issue tools like get_issue. However, it is almost a restatement of the tool name and does not clarify what 'bulk' means, what issue identifiers are accepted, or what distinguishes this from search-based issue retrieval.

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 get_issue or JQL search tools. The schema implies issueIdsOrKeys, but the description provides no conditions, exclusions, or reasons to prefer this tool.

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

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

With no annotations provided, the description carries the full disclosure burden, and 'Create component' only signals a mutating operation — information already carried by the name itself. It says nothing about permissions, side effects, idempotency, or what happens on duplicate names. Slightly more informative than a bare noun but far short of what an unannotated mutation tool requires.

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 words with no redundancy, but this is under-pecification rather than conciseness. A tool with a 16-field nested request body and no output schema cannot be usefully described in a single phrase. There are no sentences earning their place because there is effectively no content.

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?

Completely inadequate for the tool's complexity: no output schema, no annotations, a nested object parameter, and 60+ siblings to disambiguate from. An agent has no way to know what a component is, which fields matter, what the response contains, or how this differs from create_version or create_issue. Nothing necesary for correct invocation is conveyed.

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% at the top level, meeting the >80% threshold, so the baseline of 3 applies even though the description adds nothing about parameters. The body description 'Request body (JSON object)' is generic, and none of the 16 nested fields are documented in the description, but the rule grants baseline credit for the covered schema. The description itself contributes zero semantic value 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 'Create component' is a near-verbatim restatement of the tool name 'create_component', making it a tautology. It fails to specify what kind of component (Jira project component, implied by the sibling set) or how it differs from the many other creation tools. No resource scope, context, or differentiating detail is provided.

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 zero guidance on when to invoke this tool versus alternatives like create_version, create_issue, or get_project_component. No context, conditions, exclusions, or alternative routing is offered anywhere in the description.

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

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

No annotations are provided and the description discloses no behavioral traits. It does not mention side effects, required fields, permissions, or result handling. The description carries almost no information beyond the tool name.

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 but under-specified rather than appropriately concise. A two-word description is not sufficient for a nested-parameter creation operation and leaves nearly all meaning to the schema.

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

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

For a tool with nested objects, no output schema, no annotations, and a large sibling set, the description is severely incomplete. An agent cannot determine how to construct a valid issue body, what the API expects, or what success looks like.

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. However, the schema descriptions are weak: body is only described as 'Request body (JSON object)' and updateHistory's description is truncated. The tool description itself adds no parameter-level meaning.

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 'Create issue' simply restates the tool name and provides a generic verb+resource pair. It does not explain what kind of issue, what system is involved, or how this differs from create_issues or edit_issue.

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 about when to use this tool versus alternatives such as create_issues, submit_bulk_create, or edit_issue. No conditions, exclusions, or prefered scenarios 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Bulk create issue' only indicates a write operation and bulk behavior; it does not mention failure modes, partial success, limits, authentication needs, 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 extremely concise, but it is under-specified rather than efficiently complete. There is no structure or additional context to help an agent understand the bulk creation semantics or request format.

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 that there is no output schema, no annotations, and a nested input body, the tool needs more contextual detail. The description does not explain how issueUpdates should be formed, what constraints exist, or what the bulk operation returns.

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% for the single body parameter, so the baseline is 3 even though the description itself adds no parameter-level meaning. The schema describes body as 'Request body (JSON object)' but does not explain the issueUpdates items; however, per the rubric, high coverage keeps this at baseline.

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 'Bulk create issue' clearly states the verb (create), the resource (issue), and the bulk qualifier, which distinguishes it from the sibling tool create_issue. This is specific enough for an agent to identify the tool's core purpose.

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 about when to use this tool versus alternatives such as create_issue, submit_bulk_edit, or bulk_fetch_issues. The description does not mention any conditions, exclusions, or preferred contexts.

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

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

With no annotations provided, the description carries the burden of behavioral disclosure. It only repeats the create/update semantics already present in the tool name, without explaining what updating entails, whether existing links are overwritten, what happens on conflict, or what permissions/effects are involved.

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 but this is under-specification rather than effective conciseness. It provides no added value beyond the tool name and does not earn its place as a helpful explanation for an upsert operation with a nested object.

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?

This is an upsert tool with no output schema, no annotations, and a complex nested body parameter. The description leaves the agent without enough context to construct a correct request body, understand update semantics, or know how the response will look or whether the operation is idempotent.

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% for the top-level parameters, so baseline is 3. The description adds no parameter meaning beyond the schema. The nested 'body' object contains fields like globalId and relationship that remain unexplained in both the description and 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 and resource: 'Create or update remote issue link.' It is unambiguous about the operation, and the 'remote' qualifier distinguishes it from ordinary issue-link tools like link_issues. It lacks richer detail but is not confusing.

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 link_issues or get_remote_issue_links. The description implies usage from the verb 'create or update,' but it does not state prerequisites, conditions, or cases where a different tool should be preferred.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the action 'create' with no information about side effects, required context, permissions, validation, or consequences. This is no more informative than the tool name itself.

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 words is under-specification rather than effective conciseness. The description is minimal but fails to communicate anything beyond the name, so it does not earn its place as a useful explanatory sentence.

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 nested body schema with many properties, no annotations, and no output schema, a two-word description is entirely inadequate. An agent cannot determine what a 'version' is, what response to expect, or how to construct a correct request.

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 even though the description adds no parameter-level meaning. The schema documents 'body' as a request object with many properties, but the description gives no hints about which fields matter or how to construct a valid version.

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 'Create version' is essentially a verbatim restatement of the tool name 'create_version'. It names the action and resource but adds no detail, and it does not distinguish this operation from sibling create tools like create_component or create_issue.

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 about when to use this tool versus alternatives. No context is provided about prerequisites, when creating a version is appropriate, or how it differs from related project/version 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?

With no annotations provided, the description carries the full burden of behavioral disclosure, but it only says 'Delete'. It does not reveal that deletion is permanent, whether special permissions are required, any cascading effects, or what happens to associated data. The minimal phrase offers no transparency beyond the obvious destructive intent.

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 only two words, but this is under-specification rather than true conciseness. It omits necessary context that could help an agent use or select the tool correctly. Every sentence should earn its place, and here the lone phrase contributes little beyond what the name already says.

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 operation with no annotations and no output schema, the description is far too sparse. It fails to mention irreversibility, required issue/comment context, or any behavioral notes. An agent on the edge between delete_comment and update_comment or get_comment gets no guidance on the consequences of the call.

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

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

Schema description coverage is 100%: both required parameters (id and issueIdOrKey) have clear descriptions in the input schema. The tool description itself adds no parameter context, but per the baseline for full schema coverage, this is acceptable. No enum or nested object complexities exist.

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 comment' is essentially a restatement of the tool name 'delete_comment'. It states a verb and resource but adds no specificity or differentiation beyond what the name already conveys. There is no mention of which comment, what context, or how it differs from sibling comment 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 provides no guidance on when to use this tool versus alternatives such as update_comment, get_comment, or add_comment. There is no mention of prerequisites, use cases, or exclusions, leaving the agent to infer usage from the name alone.

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

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

With no annotations provided, the description carries the full burden of disclosing destructive behavior and side effects. It merely says 'Delete issue' and does not state that deletion is permanent, may cascade to subtasks, or may require specific 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?

At two words, the description is minimal, but this is under-specification rather than effective conciseness. It lacks front-loaded behavioral or usage context, so it fails to earn a higher score.

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?

This is a destructive mutation tool with no annotations, no output schema, and a very sparse description. Critical context such as irreversibility, subtask behavior, permission requirements, and how the deleteSubtasks parameter affects the operation is completely absent.

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 documents both parameters including the enum and default for deleteSubtasks. The description adds no parameter-level meaning, but the baseline of 3 applies because the schema already 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 'Delete issue' simply restates the tool name, which is a tautology. It identifies the general action and resource but provides no differentiation from sibling tools like submit_bulk_delete, delete_issue_link, or delete_issue_property.

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 submit_bulk_delete for bulk operations or delete_issue_link for removing links. The description does not mislead, but it offers no contextual usage direction.

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

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

No annotations are provided, and the description only says 'Delete issue link'. It does not disclose whether deletion is permanent, requires special permissions, or affects related data. The description carries no behavioral information beyond the operation itself.

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, but it merely repeats the tool name and does not add value. Under-specification is not true conciseness; a useful description would include at least one distinguishing detail or usage hint.

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 deletion tool with no annotations and no output schema, the description should clarify scope, side effects, or distinctions from related deletion tools. None of this is present, leaving an agent to guess whether this applies to standard issue links or remote issue links.

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

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

The schema has 100% description coverage for the single parameter linkId, so the schema already explains the parameter. The description adds no additional meaning about linkId format, provenance, or how to obtain it, but the baseline of 3 applies due to full schema 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 states the verb 'Delete' and the resource 'issue link', which is clear and unambiguous. However, it does not distinguish itself from the sibling tool delete_remote_issue_link_by_id, which is a related but distinct deletion 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?

There is no guidance on when to use this tool versus alternatives like delete_remote_issue_link_by_id or get_issue_link. The description simply restates the tool name with no context for when it is the appropriate choice.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Delete issue property' signals a destructive action but does not explain whether deletion is permanent, whether it fails for missing properties, or whether any related data or history is affected.

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—only three words—and contains no unnecessary text. However, this is under-specification rather than effective conciseness, since it omits even brief context about effects, usage, or prerequisites.

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 operation with no annotations and no output schema, the description is incomplete. It does not address failure modes, irreversibility, permission requirements, or how the response is structured, leaving an agent without enough context to invoke the tool confidently in an operational scenario.

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 both parameters are adequately described in the schema itself. The description adds no additional parameter meaning, but given the high schema coverage, 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 (delete) and a specific resource (issue property), which clearly differentiates it from siblings like get_issue_property and set_issue_property. However, it does not define what an issue property is or clarify its relationship to issues, leaving some ambiguity for an agent encountering the term for the first time.

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 about when to use this tool versus alternatives such as set_issue_property or get_issue_property. The description does not mention prerequisites, side effects, or conditions that would make deletion 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description only states the action; it does not confirm whether the deletion is permanent, whether it affects linked issue data, whether permissions are required, or how the response appears. For a destructive operation this is a significant gap.

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

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

The description is a single short sentence with no filler. It is front-loaded and every word earns its place, though it lacks additional useful context like behavior or return values.

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 two-parameter delete operation with full schema coverage, the description is minimally adequate. It correctly identifies the resource and identifier, but lacks explicit destructive-behavior warnings and any guidance about output or side effects.

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 both parameters. The description maps naturally to linkId and issueIdOrKey, but adds no extra meaning beyond the schema.

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

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

The description states a specific verb ('Delete'), resource ('remote issue link'), and the key identifier ('by ID'). It distinguishes this from the sibling get_remote_issue_link_by_id and create_or_update_remote_issue_link, and clearly aligns with the input schema's linkId parameter.

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: deleting a specific remote issue link by its ID, paired with the issue ID/key. It does not explicitly state when to use it over alternatives or mention any conditions, but the sibling context makes the fundamental use case 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states that the tool deletes a worklog, without mentioning whether the deletion is permanent, how it affects issue time estimates, notifications, or any other 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 extremely short but under-specified rather than genuinely concise. It has no structured content, no sentence that earns its place beyond restating the tool name, and omits important context that could be conveyed in minimal additional text.

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 operation with seven parameters, no output schema, and no annotations, the description is severely incomplete. It does not explain required inputs, behavior, return value, or side effects, leaving an agent without enough information to invoke the tool correctly and 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 description coverage is 100%, and the schema already documents all seven parameters. The description adds no parameter-level meaning, but since the schema carries the burden, 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 'Delete worklog' is a direct restatement of the tool name delete_worklog. It names the action and resource but adds no additional specificity about scope, target, or effect, so it qualifies as a tautology rather than a substantive purpose statement.

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 about when to use this tool versus alternatives. Sibling tools such as update_worklog, add_worklog, and get_worklog exist, but the description does not clarify when deletion is appropriate or how it differs from these related 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?

There are no annotations, so the description bears the full burden of disclosing side effects. 'Transition issue' implies a state-changing workflow operation but says nothing about permissions, reversibility, validation errors, or the fact that the body must specify a valid transition.

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 words is concise but crosses into under-specification. There is no fluff, but the description is too short to serve as a useful guide for a tool with a nested request body and several sibling variants.

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

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

With no output schema, no annotations, and a nested body schema, the description is far too incomplete. An agent cannot tell what transition values are acceptable or what the result of a successful transition will look like.

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?

Parameter schema coverage is 100%, so the schema already documents issueIdOrKey and gives the body shape. The description adds no semantic detail about what should go in 'transition' or 'fields', but it does not need to compensate much because the schema is present.

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 phrase 'Transition issue' states a clear verb and resource: the tool changes an issue's workflow status. However, it is too vague to distinguish do_transition from nearby siblings such as submit_bulk_transition or get_transitions, and it does not explain what a transition involves.

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 given about when to use this tool versus alternatives. An agent must infer from the name that it applies to a single-issue workflow transition, and it is not told to call get_transitions first or to use submit_bulk_transition for multiple issues.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure, but it reveals nothing beyond the fact that an edit occurs. It fails to mention notification behavior, screen security overrides, whether the issue is returned, or any side effects, making it nearly useless for predicting tool behavior.

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, but this is under-specification rather than conciseness. 'Edit issue' earns no space because it merely repeats the tool name without conveying any useful, non-redundant 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?

This is a complex tool with seven parameters, a nested request body, and many related sibling tools, yet the description provides no context about how to structure an edit, what the response contains, or how this differs from other issue-modification tools. The absence of an output schema and annotations makes this even more inadequate.

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 of 3 applies. The description itself adds no parameter semantics, but the input schema already documents all seven parameters, including the nested body object, issueIdOrKey, expand, notifyUsers, returnIssue, and override flags.

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