Server Quality Checklist

Tool Scores

• list_practice_promptsA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds beyond that: it runs no model, spends nothing against the daily scoring allowance, and counts against the per-minute request window. This gives the agent information about side effects and rate-limit behavior not captured in annotations. No contradictions.

  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 moderately sized and information-dense. The core purpose is front-loaded, followed by cost and rate-limit details, and then a legal disclaimer. The legal section is less functional but not excessive; the structure is logical and every sentence carries relevant information except the trademark boilerplate.

  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 three well-documented parameters, no output schema, and straightforward behavior, the description provides all needed context: what is returned (prompts with ids), which task types, cost implications, and rate-limit behavior. An agent can invoke this tool correctly without ambiguity.

  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 100%, so all three parameters are documented with meaning in the schema. The description does not add extra semantics for the parameters beyond what the schema already provides, only reiterates the task_type omission behavior which is already in the schema. Baseline 3 applies.

  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 ('List') and resource ('Writing practice prompts from the Reach120 bank'), and enumerates the two task types covered. It also hints at the primary use case by mentioning the id that is passed to score_writing_response, which distinguishes it from siblings. Purpose is unambiguous and differentiates from get_practice_prompt and score_writing_response.

  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 gives clear context for when to use: it returns prompts with the id needed for scoring, and it explains cost implications (no scoring allowance usage, but counts against request window). However, it does not explicitly state when NOT to use it or mention alternatives by name, though the sibling list exists. The guidance is sufficient for an agent to decide.

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

• get_practice_promptA
  4.3/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint and openWorldHint, but the description adds that the tool 'Reads a stored row and runs no model,' which clarifies that no AI generation happens and the result is deterministic. This is useful context beyond the annotations, and it does not contradict them.

  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 functional description is just two sentences, front-loading the main action and expected result. The trademark disclaimer is extra but legally necessary and does not bloat the description. Every sentence earns its place.

  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?

  For a single-parameter fetch tool with no output schema, the description adequately conveys what the caller gets (the full scenario/discussion context) and that it is a read-only database lookup. Nothing vital is missing for correct invocation.

  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 fully documents item_id, including its meaning ('The prompt id returned by list_practice_prompts') and constraints (minLength 1). The description adds no further parameter information, so the baseline 3 applies given the 100% schema 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 clearly states the action ('Fetch a single Writing practice prompt by its id') and the resource, and specifies it includes the full scenario or discussion context. The use of 'single' and 'by its id' distinguishes it from sibling list_practice_prompts, and 'runs no model' contrasts with score_writing_response.

  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 implies usage: the caller needs an id to fetch a specific prompt, which is a clear precondition. However, it does not explicitly point to list_practice_prompts for obtaining the id, nor does it state when to prefer this over alternatives. The parameter description in the schema partially compensates, so this is not a complete miss.

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

• score_writing_responseA
  4.8/5.0
  Behavior5/5

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

  Beyond the annotations, the description discloses that the call is a metered AI scorer drawing on the daily spend ceiling and that it refuses with a machine-readable code rather than silently falling back to a cheaper engine. It also includes the ETS non-affiliation disclaimer, all of which is useful behavioral context not present in the annotations.

  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 front-loaded with purpose and usage, then adds behavioral and legal context. It is slightly longer than necessary due to repeated ETS disclaimer phrasing, but every major section earns its place.

  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 output schema, the description still covers the return value, the metering behavior, the spend limit refusal, the parameter selection rule, and where to find response shapes and error codes. For a tool of this complexity, it is complete enough for an agent to invoke it correctly.

  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 100%, so the schema already documents each parameter. The description adds meaningful selection semantics by explaining the either/or relationship between item_id and task_type plus prompt, and clarifies that prompt is only for inline coursework. This goes beyond the schema baseline.

  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 and resource: score a learner's written response to a TOEFL iBT Writing task and return an automated practice score with a rationale. This clearly differentiates it from the sibling prompt-list and prompt-retrieval tools.

  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 tells the agent how to choose between item_id and task_type plus inline prompt, and references the prompt tools as the source of item_id. This gives a clear selection rule without leaving the agent to infer the param relationship.

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