Server Quality Checklist

Tool Scores

• complete_todoC
  2.7/5.0
  Behavior2/5

  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 implies a mutation by marking completion state, but it does not disclose whether the operation is idempotent, what happens for missing todos, permission requirements, or any 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.

  Conciseness4/5

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

  The description is a single sentence with no filler and a clear subject-verb-object structure. It is economically written, though the brevity leaves out meaningful usage and parameter detail.

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

  Completeness2/5

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

  For a simple two-parameter tool, the core action is stated, but with zero annotations, zero schema descriptions, no output schema, and no differentiation from update_todo, an agent lacks key context to invoke it confidently and predict its effects.

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

  Parameters2/5

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

  Schema description coverage is 0%, so the description should compensate for undocumented parameters. The phrase 'complete or incomplete' faintly maps to the completed boolean, but the description adds no real explanation of todo_id or how the completed value behaves beyond what the schema already shows.

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

  Purpose4/5

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

  The description names a specific verb ('mark'), a resource ('todo'), and the two states it toggles between ('complete or incomplete'), which clearly identifies the operation. It does not explicitly distinguish this from update_todo, but the completion-specific focus makes the core purpose readable.

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

  Usage Guidelines2/5

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

  There is no guidance about when to use complete_todo versus update_todo or any other sibling tool. The phrase 'one authenticated user's' hints at scope, but the description never states exclusions or directs the agent to alternatives for other todo mutations.

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

• update_todoC
  2.8/5.0
  Behavior2/5

  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 states the mutation action but does not disclose return behavior, error conditions, permission requirements, or how null values in the input schema affect existing fields. It only adds that the todo belongs to the authenticated user, which is marginal.

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

  Conciseness4/5

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

  The description is a single efficient sentence with no redundant wording. It is not overly verbose, though it is brief enough to border on under-specification.

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

  Completeness2/5

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

  For a simple update tool with no annotations or output schema, the description is incomplete. It does not clarify important behaviors such as whether omitted parameters leave fields unchanged while null parameters clear them, or what the tool returns after a successful update.

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

  Parameters1/5

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

  Schema description coverage is 0%, and the description names none of the four parameters (day, content, goal_id, todo_id). 'Provided fields' gives no meaning beyond the schema's field names, so the description fails to compensate for the schema's lack of descriptions.

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

  Purpose5/5

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

  The description clearly states the operation ('Update'), the resource ('todo'), the scope ('one authenticated user's'), and the partial nature ('provided fields'). This distinguishes it from sibling tools like create_todo, complete_todo, and delete_todo.

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

  Usage Guidelines2/5

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

  The description gives no explicit guidance on when to choose update_todo over alternatives. It does not mention that complete_todo should be used for marking complete, nor does it provide any exclusions or prerequisites. Usage is only implied by the verb 'Update'.

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

• create_todoB
  3.4/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It discloses that the operation is for the authenticated user and that the date defaults to today in Asia/Seoul, which adds useful behavioral context. It does not mention persistence, idempotency, or side effects beyond creation.

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

  Conciseness4/5

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

  The description is two sentences with no filler and the primary operation is front-loaded. It is concise and readable, though it sacrifices completeness for brevity.

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

  Completeness2/5

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

  For a 3-parameter create tool with no output schema and no annotations, the description is under-specified. It does not clarify what a goal_id is for, what the response contains, or the exact format expected for the day parameter. The timezone default is helpful but not enough.

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

  Parameters2/5

  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 all parameters. It adds semantic meaning for 'day' by explaining the default timezone behavior, but says nothing about 'content' or 'goal_id'. The purpose of 'goal_id' is entirely unexplained.

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

  Purpose5/5

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

  The description states a specific verb ('Create') and resource ('a todo'), and scopes it to the authenticated user. This clearly distinguishes it from sibling tools like get_todo, update_todo, complete_todo, and delete_todo.

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

  Usage Guidelines3/5

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

  The usage context is implied: use this when creating a new todo. However, there is no explicit guidance about when not to use it or how it relates to alternatives such as update_todo or complete_todo.

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

• delete_todoA
  3.7/5.0
  Behavior3/5

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

  With no annotations, the description must carry side-effect information. It discloses the auth/ownership boundary ('authenticated user's') and the targeted scope ('by ID'), but it does not state that deletion is permanent/irreversible or describe not-found/authorization error behavior.

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

  Conciseness5/5

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

  One concise, front-loaded sentence with no filler. Every word contributes scope or targeting information.

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

  Completeness3/5

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

  For a one-parameter delete operation, the core invocation is captured: target and authorization scope. Missing irreversibility/error/return details are real gaps, especially with no annotations and no output schema, but the tool's complexity is low enough that 3 reflects an adequate-but-minimal definition.

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

  Parameters3/5

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

  Schema description coverage is 0%, and the description only partially compensates: 'by ID' maps todo_id to the target todo's identifier, and 'authenticated user's' hints that the ID must reference the caller's own todo. It does not explain how to obtain the ID or any format constraints beyond the schema.

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

  Purpose5/5

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

  States a specific verb ('Delete') and resource ('one authenticated user's todo') with the targeting method ('by ID'). Among the sibling tools, this is the only deletion tool, and the description makes that role unambiguous.

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

  Usage Guidelines3/5

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

  Implies when to use it: when a single todo of the currently authenticated user needs to be removed by ID. It does not explicitly compare with alternatives like complete_todo or update_todo, but the auth/ownership scope provides some selection context.

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

• get_todoA
  3.7/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the behavioral burden. It adds useful context about authenticated-user scoping and single-item retrieval, but it does not disclose what happens when the todo is not found, whether the operation is read-only in explicit terms, 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.

  Conciseness5/5

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

  The description is a single, focused sentence with no filler. The key information—action, resource, ownership scope, and lookup key—is front-loaded and immediately usable.

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

  Completeness3/5

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

  For a single-parameter read operation, the description covers the core calling intent. However, with no output schema and no annotations, return value details and error behavior are left unexplained, which leaves gaps for an agent relying solely on this definition.

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

  Parameters3/5

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

  The schema only defines todo_id with a title and minLength, and schema description coverage is 0%. The description adds minimal meaning by indicating that the ID is used to select the todo, but it does not explain where the ID comes from, its expected format, or any constraints beyond the schema.

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

  Purpose5/5

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

  The description uses a specific verb ('Get') and resource ('one of the authenticated user's todos'), with a clear selection mechanism ('by ID'). It is immediately distinguishable from sibling list_todos because it explicitly refers to a single todo rather than a collection.

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

  Usage Guidelines3/5

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

  The intended use is implied: call this when you have a todo_id and need that specific todo. However, it does not explicitly state when to prefer list_todos for multiple todos or mention any exclusions, so the guidance is only inferred rather than stated.

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

• list_todosA
  4.4/5.0
  Behavior4/5

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

  With no annotations, the description carries the behavioral disclosure burden. It explains that the todos are scoped to the authenticated user, that the query is date-based, and that the default date is today in Asia/Seoul—useful behavior beyond the bare function name.

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

  Conciseness5/5

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

  A single sentence with no filler: it states the action, the scope, the parameter, and the default behavior. Every word earns its place.

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

  Completeness4/5

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

  For a simple list operation with one optional parameter and no output schema, the description is sufficiently complete. It captures scope, default behavior, and timezone context; the return shape is reasonably inferable from the tool's name and domain.

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

  Parameters4/5

  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. It effectively explains the single 'day' parameter as a date filter and clarifies that null/default means today in Asia/Seoul, adding meaning beyond the raw schema.

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

  Purpose5/5

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

  The description uses a specific verb ('List') and resource ('the authenticated user's todos') and clearly scopes the operation to a date. This distinguishes it from siblings like get_todo, which retrieves a single todo, and create_todo, which creates one.

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

  Usage Guidelines4/5

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

  The description gives clear context for when to use the tool: to list a user's todos for a particular date, defaulting to today. It does not explicitly mention alternatives or exclusions, but the date-scoped listing use case is evident.

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