Server Quality Checklist

Tool Scores

• get_projectsA
  4.7/5.0
  Behavior4/5

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

  No annotations provided, so description must carry full burden. It discloses pagination to completion and the return format. It does not explicitly state it's safe/idempotent, but the read nature is clear. Minor omission prevents a 5.

  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?

  Three concise sentences, front-loaded with the core function. Every sentence adds value: returns all projects, use case, reminder about apply_changes. 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?

  Given no parameters, no output schema, and a simple return, the description is complete. It explains the purpose, usage scenario, and relationship to sibling tools. Agent has all necessary info.

  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?

  No parameters exist, and schema coverage is 100% (empty). Baseline for 0 parameters is 4. Description adds no parameter info but doesn't need to. It adds context about what the tool does.

  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 precisely the action: 'Returns every Todoist project as { id, name }'. It specifies the verb (returns) and resource (projects), and distinguishes from sibling tools by noting that apply_changes handles automatic creation.

  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?

  Explicitly states when to use: 'to check whether a Someday/Maybe retirement project already exists'. Also clarifies when NOT to create a project manually because apply_changes' move_to_project action finds-or-creates. Provides clear context and alternatives.

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

• apply_changesA
  4.8/5.0
  Behavior5/5

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

  With no annotations, the description fully discloses behavioral traits: validation rejects the entire batch if any item is malformed, execution is per-item with independent success/failure reporting, and no delete action exists. This covers key safety and execution model details.

  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 long but well-structured with clear sections for usage guidelines, action details, and validation behavior. Every sentence adds value given the complexity of six action types. Slightly verbose but justified; could be trimmed slightly without losing meaning.

  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 description covers input comprehensively and mentions per-item result reporting, but does not provide output schema or detailed error response format. For a mutation tool with no output schema, this is fairly complete; minor gap on output specifics.

  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?

  Since schema description coverage is 0%, the description adds extensive meaning by detailing each action type (reschedule, set_priority, etc.), their required params, and nuances like priority mapping (1-4, 4 highest) and project name matching (case-insensitive, auto-create). This is far 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 clearly states the tool executes an explicit list of approved changes against Todoist, which is a specific verb+resource. It distinguishes itself from sibling read-only tools (get_overdue_tasks, get_projects) by being a mutation tool. The phrasing 'ONLY call this with changes the user has explicitly approved' reinforces its unique purpose.

  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 first paragraph provides explicit instructions on when to use (only with explicit user approval), what not to do (never infer, batch, or add unconfirmed changes), and what actions are missing (no delete, no split). This gives clear guidance on appropriate usage and distinguishes from alternatives.

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

• get_overdue_tasksA
  4.8/5.0
  Behavior5/5

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

  No annotations provided, but the description takes full responsibility, stating 'This tool is READ-ONLY and writes nothing.' It also details output fields, including the conditional timesRescheduled, and explains priority inversion without contradiction.

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

  Conciseness4/5

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

  The description is detailed but well-structured with clear sections. Each sentence adds value; however, it could be slightly more concise without losing meaning.

  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?

  No output schema, but the description fully documents the output format, field meanings, and interpretation logic (priority inversion, reschedule vs retire decision). All necessary context is provided for a zero-parameter, output-only tool.

  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?

  No parameters (input schema empty), so baseline is 4. The description adds no param info, but no param info is needed; the context is fully covered elsewhere.

  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 specifies that the tool returns overdue Todoist tasks as weekly-review candidates, listing exact fields. It is distinct from sibling tools like apply_changes and get_projects, which have different purposes.

  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?

  Explicitly states when to use (weekly review), provides step-by-step post-call workflow (propose fixes per task, get user approval before calling apply_changes), and includes signal-reading guidance for deciding between rescheduling and retiring tasks.

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