Words in Context

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

Beyond the readOnlyHint annotation, the description discloses the full return content: correctness, the right option, why it fits, why the chosen option was wrong, and why every distractor fails. It also adds a crucial behavioral expectation — read distractor reasons aloud even on correct answers — which materially changes how an agent should use the result.

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 compact but information-dense: it opens with the core purpose, enumerates the returned content, includes a directly actionable pedagogical instruction, and ends with input requirements. Every sentence earns its place, and the most important operational detail about reading distractor reasons is highlighted.

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?

With no output schema, the description fully carries the burden of explaining return values, and it does so explicitly. It also covers the input source and gives behavioral guidance, making the tool safely and correctly invocable without needing to infer missing details.

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 100%, so the schema already documents both id and choice. The description restates the same information ('id from a draw response', 'zero-based index') without adding new meaning, earning the baseline score.

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 'Check' with a clear resource ('an answer to a practice item') and states the output ('get the teaching content'). It is immediately distinguishable from sibling tools draw_items and generate_items, which create or retrieve items rather than evaluate answers.

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 clearly implies the workflow by stating that the id comes from a draw response, so the agent knows this tool is used after draw_items. It does not explicitly name alternatives or state when not to use this tool, but the workflow context is strong enough to guide correct 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?

The description goes far beyond the readOnlynHint annotation by disclosing important behavioral traits: the response deliberately omits answer indices and explanations to avoid leaking answers, out-of-range count values are refused rather than clamped, same seed yields reproducible results, and the question format follows digital-SAT vocabulary testing. This gives the agent strong expectations about what the tool will and will not return.

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 longer than minimal, but every section earns its place: purpose, use cases, critical no-answer caveat, parameter summary, and format note. Some parameter details repeat the schema, but they are compact and useful for an agent that may not open the schema. It is well-structured 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?

There is no output schema, so the description carries the burden of explaining the response shape. It does so well: no answer index, no explanations, each item is a sentence with one blanked word and four options, and items have ids used with check_answer. For a read-only, deterministic draw tool, this is complete enough for correct selection and 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 100%, so the baseline is 3. The description largely restates what the schema already documents: count range/default, difficulty levels, theme values, and seed behavior. It adds no significant new parameter semantics beyond what is already in the schema; the refusal behavior for count is also already in 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 opens with a specific verb+resource: it draws words-in-context vocabulary practice questions from a curated, human-written bank. It also differentiates itself from siblings like generate_items by emphasizing that it is free, deterministic, and costs no inference, so an agent can tell it apart.

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?

It explicitly lists use cases: quiz a learner, build a practice set, or inspect what a question looks like. It also tells the agent to call check_answer for answers, which helps route the workflow correctly. It does not explicitly name generate_items as the alternative for generative/non-deterministic draws, so it stops short of a full when-to-use-when-not-to-use guide.

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?

The description goes well beyond the readOnlyHint/openWorldHint annotations: it discloses per-call cost with exact prices, the 10-calls-per-day cap, that output is NOT human-reviewed, that every response carries a caveat, and the 503 failure mode. This is exactly the operational context an agent needs before spending money.

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?

Front-loaded with the core purpose and the critical paid-tier warning, with each paragraph serving a distinct role (cost, model selection, limits, quality caveat, fallback). Slightly verbose — 'which is the hard part of a good practice item/question' appears twice — but every section earns its place for a paid 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?

For a complex paid tool with no output schema, the description covers all invocation-critical info: minimum/maximum inputs, rate limit, cost model, review-quality warning, and error handling with fallback. It even hints at the response shape ('Check the answer and the distractor reasons'), so an agent can call this safely without guessing.

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 coverage is 100% so the baseline is 3, but the description adds real value: for 'model' it gives exact per-item prices and a decision rule (economy for straightforward prose, standard for tempting distractors), and for 'source' it clarifies 'the material they got wrong.' The count limit of 5 is reinforced. Only 'difficulty' gets no added meaning.

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?

States a specific verb and resource ('Generate new practice items from a passage the learner supplies') and immediately distinguishes itself from the sibling draw_items with 'unlike the curated bank.' An agent can tell exactly what this tool does and how it differs from the alternative.

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?

Explicitly routes the agent: 'Prefer draw_items unless the learner specifically needs questions from their own material' and 'fall back to draw_items' on 503. It names both the when-to-use and when-not-to-use conditions with the sibling tool.

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