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

No annotations are present, so the description bears full responsibility. It discloses key behavioral traits: read-only nature, batched export, default page size of 5000, and no limit on total rows. This goes beyond the schema by clarifying execution semantics. However, it does not mention how output is delivered (e.g., file path vs. content) or any permission requirements.

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. Every phrase adds value: read-only, export CSV, batching, default page size, and total row limit. No wasted words.

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

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

Given the presence of an output schema, the description does not need to spell out return values. It adequately covers the core behavioral aspects: batching, page size, unbounded rows. But it lacks information about how the CSV is returned or prerequisites like instance configuration, which are not covered elsewhere.

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 0%, and the description adds minimal parameter meaning. It mentions page_size default and max_rows behavior ('默认每页 5000 行，不限制总行数'), but does not explain instance_name, database, sql, schema, or filename. Most parameter meanings (like instance_name) are not obvious, leaving the agent to guess.

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 '将只读查询分批导出为 CSV' clearly states a specific verb (exporter), resource (read-only query), and output format (CSV) with a batching mechanism. It distinguishes from siblings like 'archery_query' which presumably returns raw results rather than exporting to CSV.

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 for read-only queries that need CSV export in batches, providing clear context but no explicit exclusion or alternative tool reference. It does not explicitly say 'use this instead of archery_query when...' but the purpose is transparent enough to infer 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?

With no annotations provided, the description carries the burden of behavioral disclosure. It adds transparency by explicitly stating 'does not perform login' (no authentication side effect) and that it returns the version. This is useful, though it does not mention other potential behavioral aspects like read-only nature or error handling, but the simplicity of a health check makes this sufficient.

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, front-loaded with the action verb '检查', and includes only essential information: what it does and what it doesn't do. There is zero verbosity or repetition.

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

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

For a zero-parameter health check with an output schema, the description fully covers purpose, non-login behavior, and expected return (version). The sibling tool names provide additional context, and the output schema handles return structure. No significant gaps exist.

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 tool has zero parameters, so schema coverage is trivially 100%. The description clarifies the tool's function, which indirectly confirms there are no inputs to worry about. With 0 params, baseline is 4, and the description does not need to add parameter-specific details.

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 ('检查' / check) and clearly states the resource (Archery accessibility) and expected output (version). It distinguishes itself from sibling tools like archery_login_status by explicitly focusing on connectivity and version rather than login status.

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 clear context for use: checking accessibility and version. It includes an explicit 'does not perform login' exclusion, which helps differentiate it from login-related tools. However, it does not explicitly name alternative tools or give positive when-to-use scenarios beyond the inherent 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?

With no annotations provided, the description carries the burden of behavioral disclosure. It uses '查询' which implies a read-only operation, and adds that instance ownership is validated by Archery, providing some context. However, it does not describe error handling, pagination, output format, or anything about side effects. It is minimally transparent but not rich.

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 clauses, front-loading the core action and adding a validation note. Every word contributes value, with no fluff. It is highly concise and well-structured.

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 simple one-parameter tool with an output schema present, so the description does not need to explain return values. However, it lacks guidance on parameter sourcing and does not clarify what 'readable instance' means in terms of prerequisites or limitations. The description is adequate for a trivial tool but leaves some gaps in context.

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

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

The schema has zero description coverage, so the description must compensate. The description mentions '指定可读实例' (specified readable instance), hinting that the instance_name parameter should refer to a readable instance and that ownership is checked. However, it does not explain where valid values come from (e.g., from archery_list_instances), nor does it provide any format or constraints beyond the schema's title. The semantic addition is minimal.

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 function: query databases in a specified readable instance. It uses a specific verb (查询) and resource (数据库), and specifies the target instance. However, it does not explicitly differentiate from sibling tools like archery_list_instances or archery_list_query_instances, though the focus on databases within an instance makes it reasonably distinct.

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 context: only for readable instances, and notes that instance ownership is verified by Archery. It does not explicitly mention when to use this tool instead of alternatives, nor does it provide exclusions or prerequisites (e.g., how to obtain valid instance names). The context is implied but not fully articulated.

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

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

With no annotations, the description carries the full burden. It discloses permission filtering and pagination behavior, which is useful, but it does not mention authentication requirements, side effects, or return format (though output schema exists). It adds some context beyond the schema but lacks explicit read-only confirmation.

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 verb and resource, with no extraneous words. Efficient and clear.

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 captures the core purpose and scope, and an output schema exists to define returns. However, the missing search parameter explanation and lack of behavioral details (e.g., authentication, error conditions) leave the description incomplete for safe and correct invocation.

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

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

Schema description coverage is 0%, so the description must compensate. The term 'paginated' suggests limit and offset semantics, but the search parameter is left unexplained. The description does not clarify how search filters results, leaving ambiguity for the agent.

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 performs a paginated query of database instances accessible to the current Archery account, specifying both verb and resource. The permission scoping and pagination help distinguish it from sibling tools like archery_list_query_instances and archery_list_databases.

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 for listing accessible instances but does not explicitly state when to choose this over alternatives such as archery_list_query_instances or archery_list_databases. No when-not-to-use guidance is provided.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It uses '查询' (query), which strongly implies a read-only operation, and specifies the account/resource-group scoping. It does not mention side effects, auth requirements, or rate limits, but for a list operation this is reasonably transparent.

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 immediately states the verb, object, and scope. There is no redundant information or filler, making it optimally concise 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?

This is a simple, parameterless list tool with an output schema available. The description fully explains what the tool returns and its scoping constraints. There are no missing details that would hinder an agent from invoking it 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?

The tool has zero parameters, so per the rubric the baseline is 4. There are no parameters to explain, and the description still adds context about the implicit scope (current account's resource group and read-only-query eligibility).

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

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

The description clearly states a specific verb ('查询'/'query') and resource ('实例'/'instances'), and adds a precise scope: instances in the current account's resource group that allow read-only queries. This distinguishes it from the sibling 'archery_list_instances', which likely lists all instances without that 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 implies when to use the tool: when you need instances that are permitted for read-only querying in the current account's resource group. However, it does not explicitly mention alternatives or when not to use it, providing only implied usage context rather than 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?

With no annotations, the description carries full burden. It only mentions permission-based scoping and pagination, but fails to disclose other behaviors such as response format, sorting, rate limits, or implications of the search parameter. Safety profile is unaddressed.

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 without wasted words. It conveys the core action and scope efficiently, fitting the conciseness criterion despite being under-specified in other dimensions.

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 is a straightforward list operation, but the description leaves gaps: search semantics, pagination details, and permission behavior are implied but not elaborated. An output schema exists, reducing the need to explain return values, yet the description is still minimally adequate.

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 0%, and the description does not compensate. Limit and offset are somewhat inferred from names, but 'search' is ambiguous—unclear whether it filters by ID, title, or content. No parameter meanings are clarified.

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 ('paginated query') and resource ('SQL workorders') with a scope ('current account has permission to view'). It distinguishes from sibling tools by resource type (workflows vs instances/databases), though it doesn't explicitly name alternatives.

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

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

No guidance is provided on when to use this tool versus alternatives like workflow_detail or workflow_status. The description implies a list operation, but there are no explicit use-case instructions or exclusions.

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

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

With no annotations, the description carries full responsibility for behavioral disclosure. It mentions using configured credentials and performing a login, but does not state whether this has side effects (e.g., creating a session), how failures are handled, or what the response indicates. This is a significant gap for a tool that performs an authentication 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, front-loaded sentence that directly conveys the purpose and result. There is no wasted verbiage, and it is appropriately sized for a simple zero-parameter 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 tool's simplicity and the presence of an output schema, the description is minimally functional. However, it does not mention prerequisites (e.g., whether credentials must be preconfigured) or how this tool relates to sibling archery tools, leaving some contextual gaps.

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 tool has zero parameters, and schema coverage is 100% (trivially). The description adds meaning by referencing 'configured username and password', implying server-side configuration rather than user-supplied arguments, which is useful context beyond the empty 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 ('login' with configured credentials) and the outcome ('confirm account can be used for MCP'), making it distinct from sibling tools that list or query resources. The verb 'login' and resource 'account' are specific.

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 phrase 'confirm account can be used for MCP' implies this tool is a prerequisite or validation step before using other archery tools, but it does not explicitly state when to use it versus alternatives, nor does it mention exclusions or preferred timing.

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 transparency. It explicitly discloses that the operation is '只读' (read-only) and imposes a 5000-row maximum, which are key behavioral traits. However, it leaves '受限' (restricted) vague and does not mention potential errors or authentication requirements.

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. Every word contributes essential information: execution type, read-only nature, single-query scope, and row limit. It is highly 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?

The tool has 5 parameters with zero schema descriptions and no annotations, so the description must cover more ground. It does cover the read-only constraint and row limit, and an output schema exists to explain return values. Yet it lacks parameter-level guidance and sibling differentiation, leaving the description merely adequate, not 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 description coverage is 0%, so the description must compensate for parameter meanings. It mentions a 5000-row limit, vaguely related to the `limit` parameter, but does not explain `instance_name`, `database`, `schema`, `sql`, or the actual use of `limit`. The parameter names are somewhat self-explanatory, but the description fails to add meaningful detail 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 '执行单条受限只读查询；最多返回 5000 行' clearly states the tool executes a single restricted read-only query with a 5000-row limit. The specific verb '执行' and resource '查询' combined with the constraints distinguish it from sibling tools like archery_export_query, which likely handles larger or exported results.

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

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

The description gives clear usage context: use for a single, read-only query capped at 5000 rows. It does not explicitly name alternatives or exclusion criteria, such as when to prefer archery_export_query, so it falls 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?

No annotations are provided, so the description must carry the transparency burden. It mentions a permission requirement ('有权查看的') but does not disclose error behavior, authentication scope, or whether the operation is read-only. This is minimal behavioral disclosure for a query 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 with no wasted words, front-loaded with the verb and resource. It is structurally efficient and easy to parse, earning a top score for conciseness.

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

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

The tool is simple (one required parameter) and has an output schema, so the description can rely on those for return details. However, it omits parameter semantics and usage context, and with no annotations, it remains only minimally viable for an agent to use 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?

The schema has zero description coverage for the workflow_id parameter, and the description does not explain it at all. Although the parameter name is transparent, the description adds no meaning beyond the schema, failing to compensate for the low 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 uses the specific verb '查询' (query) and clearly identifies the resource as 'SQL 工单审核或执行明细' (SQL workflow audit/execution details). It distinguishes this tool from siblings like archery_workflow_status and archery_list_workflows by focusing on detail retrieval for a single workflow. The mention of '有权查看的' (with permission to view) adds helpful scope.

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 archery_workflow_status or archery_list_workflows. It does not mention exclusions or prerequisites beyond permission, so the agent receives no context for tool 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?

No annotations are provided, but the description notes a permission requirement ('有权查看的') and the verb '查询' implies a read-only operation. However, it does not disclose other behaviors like error handling or response format, which would be expected given the lack of 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, focused sentence that immediately states the action and target. There is no redundancy or unnecessary detail, making it highly concise and well-structured.

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 tool with one parameter and an output schema, the description covers the core purpose, permission constraint, and read-only nature. However, it lacks any guidance on typical usage scenarios or edge cases (e.g., how to obtain workflow_id), so it is not fully 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?

The schema description coverage is 0% and the description does not explain the workflow_id parameter. Although the schema's title 'Workflow Id' provides some context, the description adds no additional meaning, failing to compensate for the low 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 ('查询' - query) and resource ('SQL 工单当前状态' - current status of SQL workflow). It specifies the scope as 'status' which is a distinct resource view, but it does not explicitly mention sibling tools like archery_workflow_detail, so it doesn't fully differentiate.

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 mention of when to use this tool versus alternatives such as archery_workflow_detail. The phrase '有权查看的' implies a permission prerequisite, but it does not provide contextual guidance or exclusions.

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