Server Quality Checklist

Tool Scores

• plan_recentA
  4.3/5.0
  Behavior4/5

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

  Explicitly declares read-only behavior and that it does not change state. No annotations are provided, so the description carries the full burden and does so well, though it could clarify ordering or recency definition.

  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?

  Description is brief and includes an Args section, but there is some redundancy (e.g., ‘Read-only — does not change any state’ could be merged). Overall well-structured.

  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 tool with one optional parameter and an output schema, the description covers purpose, usage, and parameter. It is complete enough without needing to detail return values.

  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 coverage is 0%, but the description adds meaning for parameter 'n' (maximum number, default 10). Could be improved with range or constraints.

  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 it lists the most recent plans for debugging/observability, with a specific verb and resource. It is distinct from sibling tools like enter_plan_mode or todo_write.

  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?

  Provides a concrete example (inspecting plan history) and mentions use without opening SQLite, but does not explicitly state when not to use or name alternatives.

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

• get_plan_mode_standardsA
  4.5/5.0
  Behavior4/5

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

  No annotations provided, so description carries full burden. Discloses that it returns standards for the duration, is not auto-injected, and gives a brief description of the return format. Lacks details on exact structure or side effects, but for a simple fetch, it's adequate.

  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?

  Well-structured: clear actionable instruction, rationale, and bullet points for return value. Every sentence adds value, no waste.

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

  Completeness5/5

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

  Complete for a parameterless tool with an output schema. Covers when to use, why, and what it returns. No gaps.

  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?

  Tool has zero parameters, so schema coverage is 100%. Baseline 4 is appropriate; description adds no parameter info as none needed.

  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 starts with a clear verb-resource pair: 'Fetch the full plan-mode rulebook.' It also situates the tool within the workflow, distinguishing it from siblings by specifying it is called after enter_plan_mode and before writing the plan.

  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?

  Explicitly states when to call: 'ONCE at the start of a plan-mode task (after enter_plan_mode, before writing your plan).' Explains why it's needed and suggests re-fetching if unsure. Does not mention when not to use, but the context is clear enough.

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

• todo_writeA
  4.5/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries full burden. It discloses destructive behavior (replaces prior state), constraints (one in_progress), and clearing via empty list. No contradictions, but lacks details on error handling or authorization.

  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 concise and well-structured, with front-loaded purpose and clear formatting for details. Every sentence adds value without redundancy.

  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?

  Given the simplicity of the tool (one parameter, output schema exists), the description covers behavior, constraints, and usage. It could mention error cases or confirmation behaviors, but overall it's thorough enough 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.

  Parameters5/5

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

  Schema coverage is 0%, but the description fully compensates by defining the structure of each todo entry, including fields, enums for status and priority, and the effect of an empty list. This provides critical meaning 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 clearly states the tool maintains the task list for the session and explains the semantics of replacing the full list on every call. It distinguishes itself from siblings which are plan mode tools.

  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?

  It explicitly says to send the FULL list on every call and that it replaces prior state. It also notes the constraint of at most one entry being in_progress. It does not explicitly mention when not to use or alternatives, but the context is clear enough.

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

• enter_plan_modeA
  4.6/5.0
  Behavior4/5

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

  With no annotations, the description properly discloses that the tool 'is non-destructive; it only marks state so the workflow is observable.' It does not mention any side effects, but it is sufficiently transparent for the agent to understand the safe, stateful nature of the tool.

  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 concise and well-structured, with a clear purpose statement, usage guidelines, a workflow bullet list, and a parameter section. Every sentence adds value without redundancy.

  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?

  Given the tool's low complexity and the presence of an output schema (which presumably describes the response), the description covers purpose, usage, and parameters adequately. It does not elaborate on the output, but the schema is expected to handle that.

  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%, but the description adds meaning for both parameters: 'reason' is a short note on why plan mode is warranted, and 'goal' is a one-line description of the plan's achievement. This compensates for the missing schema 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 tool's function: 'Enter plan mode before attempting any complex, multi-step, or file-modifying task.' It specifies the verb (enter) and resource (plan mode), and distinguishes it from siblings like exit_plan_mode and todo_write.

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

  Usage Guidelines5/5

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

  The description provides explicit when-to-use guidance: 'Use this PROACTIVELY for non-trivial coding, refactoring, or destructive operations.' It also details the subsequent workflow: research, todo_write, exit_plan_mode, and wait for approval, while advising against write/edit/exec during planning.

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

• exit_plan_modeA
  4.7/5.0
  Behavior4/5

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

  With no annotations, the description discloses key behaviors: the tool blocks the agent run until user decision, and explains the approval flow. It also mentions deferred approval on certain clients. Lacks mention of side effects or permissions, but is sufficient for the tool's function.

  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 concise and well-structured: purpose first, then conditions, then arguments. Every sentence adds value without redundancy.

  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?

  The tool has 2 parameters and no output description despite having output schema. The description covers usage and parameters well but omits return value details. Still complete enough for agent decision-making.

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

  Parameters5/5

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

  The description explains both parameters: plan is 'The full step-by-step plan, in markdown' and todos is 'Optional updated todo list to persist alongside the plan.' This adds significant meaning beyond the schema, especially given 0% schema description coverage.

  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 starts with a clear verb and resource: 'Submit your completed plan and wait for user approval.' It distinguishes itself from siblings like enter_plan_mode by specifying that this ends plan mode with user approval.

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

  Usage Guidelines5/5

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

  It explicitly states when to call it: 'Call this ONLY after you have a concrete, actionable plan.' It details the two possible outcomes (approve/deny) and behavior on different clients, providing clear guidance on when to use and what to expect.

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