GermanExam.pro

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

Annotations say readOnlyHint=false and idempotentHint=true, but the description supplies the reasoning and side effects the annotations cannot: the result is persisted with the exercise attempt and only one evaluation is allowed per exercise. It also discloses the return payload (correct count, which ones, solution plus short explanation, listening transcript) and the auth scope, all beyond structured fields.

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 action and the source of attempt_id, and most sentences carry new information (persistence, auth scope, return contents). It runs long and repeats the 'never guess answers' rule already present in the answers parameter description, which is the only real waste.

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 an output schema present, return values need only light framing, and the description goes further by naming what comes back and noting the listening transcript. Prerequisites, auth behavior, side effects and the one-evaluation rule are all covered; nothing needed to call it correctly is missing.

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 restates the answer format ('task number and letter; for marking tasks the numbers of the marked entries') rather than adding syntax or edge cases beyond the schema, and it does not mention the optional feedback_language parameter at all.

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 ('check the user's answers to an exercise') and anchors it to the sibling that produces the required identifier ('from get_practice_exercise, using its attempt_id'). An agent can distinguish it from evaluate_text, get_evaluation_result and get_practice_exercise without opening any schema.

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?

Explicit prerequisites and alternatives are given: must come from get_practice_exercise with its attempt_id, one evaluation per exercise, works with or without sign-in, and only the caller's own exercises are checkable. It also gives a strong negative instruction ('Never fill in, guess or correct answers for the user'), which is exactly the failure mode an agent would otherwise fall into.

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?

Goes well beyond the annotations: it discloses that the call is asynchronous (returns a job_id immediately rather than the result), that output varies by account tier (guest sees marked passages and top risk; free account adds verdict; out-of-scope requests get a short note and link), and that signed-in users' text and results are persisted — consistent with readOnlyHint=false and idempotentHint=false.

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 trigger condition and dense with load-bearing detail, but the sentence about guest-tier results is muddy — the parenthetical '(a user without an account can use one part)' is ambiguous and reads as leftover drafting. Slightly long, though nearly every sentence earns its place.

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 5-parameter, tiered, asynchronous tool with an output schema, this covers everything an agent needs: trigger, scope, async completion path, account-dependent behavior, persistence, and negative cases. Return-value details are correctly omitted because an output schema exists.

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 explains exam, part, task, text and feedback_language; the baseline is 3. The description adds only the external length guidance ('about 50 to 900 words') and the 'send only the user's own text' constraint, which is useful but does not meaningfully extend parameter 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 ('evaluated the way an examiner would' a 'German text they wrote themselves') plus the exact scope: the writing section of TestDaF, DSH, Goethe C1, telc C1 Hochschule, telc C1 allgemein. It is clearly separable from siblings like get_evaluation_result and lookup_exam_rubric because it names the async hand-off explicitly.

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?

Gives an explicit trigger ('Use this when the user wants a German text they wrote themselves'), an explicit exclusion list ('Not for: translations, grammar questions, exam tasks, phrase lists, texts the user did not write, or other languages'), and points to the follow-up tool get_evaluation_result for retrieval. Nothing about selection is left to inference.

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?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds real behavioral information on top: the three possible status outcomes, what 'done' yields with versus without sign-in (verdict vs reduced report), the card rendering, and the ownership restriction. That is exactly the kind of context annotations cannot convey.

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?

Three sentences, front-loaded with the triggering action and followed by outcome and access notes. Slightly dense phrasing in 'with the verdict or, without sign-in, the reduced report; shown as a card' but nothing is wasted.

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 an output schema present, return-shape detail is technically redundant, yet the description usefully frames the status semantics for a polling tool. It omits guidance on whether to re-poll, expected delays, or job_id expiry, which are the remaining gaps for a job-result endpoint.

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% and the single job_id parameter is fully documented in the schema, including its origin. The description only restates that job_id comes from evaluate_text, adding no format or constraint detail beyond the schema's length bounds. Baseline 3 applies.

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 ('collect the result of an evaluation') and ties it to the exact sibling that produces the input ('started with evaluate_text, using its job_id'). An agent can distinguish this retrieval tool from evaluate_text without opening either schema.

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 trigger condition is explicit: use this after an evaluation was started with evaluate_text. It also clarifies sign-in is not required and that only the caller's own evaluations are collectible. There is no explicit 'when not to use' statement, but the polling-after-start framing leaves little ambiguity.

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?

Annotations declare the tool is not read-only and not idempotent, but the description goes well beyond that: it discloses that the solution is withheld, that attempts are stored for 30 days, that anonymous users get exactly one part before an account is required, and how account-gated requests are answered (short note plus link). It also states a key agent constraint — never solve the exercise or reveal/guess answers — which no annotation conveys.

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 trigger condition and the return format, then layers quotas, storage, and exclusions in a logical order. It is dense and somewhat long for a single paragraph, but nearly every sentence carries non-redundant information an agent needs.

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?

An output schema exists, so return values need not be re-explained; given that, the description covers what remains: auth/quota behavior, data retention, safety constraints around answers, and the sibling to call next. Nothing an agent needs in order to invoke this correctly is missing.

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% and all three enums are documented in the schema itself, so baseline is 3. The description adds indirect meaning about the returned exercise shape (text with questions vs. recording with questions) but does not explain the 'part' parameter or any parameter behavior beyond 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?

States a specific verb and resource ('Returns one exam-format exercise') and constrains it to German C1 exams (TestDaF, Goethe-Zertifikat C1, telc Deutsch C1 Hochschule) for reading or listening. It also distinguishes itself from siblings by naming check_practice_answers as the follow-up and evaluate_text as the writing 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?

Gives explicit trigger conditions ('when the user wants to practise reading or listening ... and asks for an exercise or the next task') and explicit exclusions ('Not for writing (use evaluate_text), speaking, grammar drills or other exams'). The alternative tool is named alongside the condition that selects it, plus the follow-up step for checking answers.

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?

Annotations already cover read-only, idempotent and closed-world behavior, and the description still adds real context: the data is drawn from published exam rubrics, the result flags where a per-criterion breakdown is the provider's own, and no sign-in is needed. It stops short of describing result shape, but an output schema exists so that burden is lifted.

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 trigger condition and scope are front-loaded and every sentence carries information: coverage, provenance, read-only status, exclusion, and the sibling hand-off. The prose is dense and slightly run-on, but there is no filler to cut.

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 only one enum parameter, a full output schema, and rich annotations, the description supplies everything left: scope, provenance, auth expectation, exclusions, and the hand-off to evaluate_text. An agent can select and call this correctly without further information.

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% and the enum already documents each exam identifier, so the baseline is 3. The description corroborates the exam list and adds the useful constraint that only the writing section rubric is returned, but contributes no syntax or format detail beyond 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?

Names a specific verb (look up) and resource (exam rubric) and narrows it precisely to the writing section of German C1 exams, listing the five exams covered. It is unmistakably distinct from evaluate_text, which it explicitly names as the grading counterpart.

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?

Gives an explicit trigger ('when the user wants to know how the writing section ... is assessed'), an explicit alternative with its selecting condition ('when the user wants their text assessed, call evaluate_text instead of estimating points'), and an explicit exclusion ('Not for other languages or exams'). Nothing is left to inference.

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