Scholarize: Study Plans, Citations, Quizzes & Flashcards

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

Annotations already declare this is not read-only and is open-world; the description adds meaningful context beyond that: the call runs against the connected student account, it consumes their plan quota, and it requires a Scholarize token obtained from Settings. That auth precondition and billing effect are exactly the kind of non-obvious behavior an agent needs, though latency/pagination-style traits are not applicable here.

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 tight sentences, front-loaded with the action and result, then usage triggers, then the prerequisite. Every sentence carries distinct information with no repetition of the schema or title.

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 two-parameter tool with no output schema, the description covers what the tool returns (a step-by-step explanation), when to use it, and the account/token prerequisite. The only gap is the absence of any explicit alternative-tool routing, which is minor here.

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%, with both 'question' and 'subject' documented in the schema, so the baseline is 3. The description adds no extra semantics (e.g., subject format, question length/scope) beyond what the schema already provides.

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 names a specific verb ('Ask ... a question') and resource ('the Scholarize Tutor') and states the output form ('step-by-step explanation'), so the tool's function is unambiguous. It does not explicitly contrast itself with the generate_* siblings, but the tutoring/Q&A framing is distinct enough from artifact generators and list_* tools that an agent can separate them.

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 gives concrete triggering phrases ('explain X', 'help me understand Y') and a category (homework/concept questions), which tells the agent when to reach for it. It stops short of naming alternatives or when NOT to use it (e.g., vs generate_flashcards for drill practice), so it is clear context without exclusions.

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 declare destructiveHint=false, openWorldHint=true and idempotentHint=false, so the safety profile is covered. The description adds "No account or email needed," which usefully tells the agent the tool works without authentication and that the email field is incidental, but says nothing about rate limits, latency, or failure modes for an open-world network call.

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 short sentences, front-loaded with what is produced and in what styles, followed by the situational trigger. Each sentence carries weight, though the auth/email sentence is the weakest and could fold into the usage sentence.

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 an 11-parameter tool with no output schema, the description never states what comes back — whether the response contains all five citations, one, or requires a style selection (no `style` parameter exists in the schema). Parameter semantics are covered by the schema, but the return shape is left to inference, which is the main gap.

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 every one of the 11 parameters is already documented in the schema, which sets the baseline at 3. The description's mention of "five styles" and "source type and details" adds no per-parameter syntax or format guidance beyond the schema, so it neither compensates nor detracts.

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 a formatted citation") plus the exact output styles (APA, MLA, Chicago, Harvard, IEEE) and the input basis (source type and details). This is clearly distinguishable from the sibling tools, which all produce study material rather than references.

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?

"Use it when a student needs to cite a book, journal article, website, or other source for an essay or paper" gives a concrete usage context and enumerates the source types that map to the `type` parameter. No exclusions or explicit sibling comparisons are offered, but the trigger condition is unambiguous.

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 mark this as a non-read-only, open-world, non-destructive, non-idempotent write. The description adds genuinely useful context beyond them: that a connected Scholarize account is a prerequisite and that output is persisted to that account. It stops short of noting whether repeated calls duplicate existing cards, which matters for an idempotentHint=false tool.

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?

Two short sentences, front-loaded with the action and inputs. There is mild redundancy between 'the connected student Scholarize account' and the trailing 'Requires a connected Scholarize account,' but it stays under control and costs little.

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 100% schema coverage, all-optional params, and no output schema, the essentials are covered: inputs, destination, and the account prerequisite. For a generation tool it would be slightly stronger if it said whether the result is returned inline or only saved to the account, but overall the agent has enough to invoke it correctly.

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 all three optional parameters. The description echoes the topic/notes inputs but adds no format, constraint, or default information (e.g., default card count) beyond what the schema provides. Baseline 3 is appropriate.

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 (generate) and resource (study flashcards), and names the two input modes: from a topic or from pasted notes. It also clarifies persistence ('saved to the connected student Scholarize account'), which distinguishes it from a pure read like list_my_flashcards. It does not, however, differentiate itself from the sibling generators (generate_quiz, generate_study_plan).

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 implies when the tool applies (you have a topic or notes to turn into cards), but never explicitly states when to choose it over generate_quiz or the other generate_* siblings, nor any exclusions. Usage is inferable rather than spelled out.

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 readOnlyHint=false, idempotentHint=false and openWorldHint=true but say nothing about persistence or prerequisites. The description adds genuinely new context: the generated quiz is written to the student's account, and an authenticated connection is required. It stops short of describing output or failure behavior.

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?

Two short sentences that lead with the action, which is the right front-loading. The second sentence restates the account requirement already implied by 'for the connected student', so there is minor redundancy.

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 simple three-parameter generator with no output schema, the description covers what is produced, where it is saved and the account prerequisite. It does not say what identifier or object comes back on success, but with no output schema that gap is modest.

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 topic, difficulty and numQuestions are already documented in the schema. The description only echoes 'on a topic' and adds no format, constraint or default information beyond what structured data provides, so the baseline of 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?

The description states a specific verb and resource: 'Generate a practice quiz on a topic', plus the scope that it is for the connected student and persisted to their account. It does not explicitly distinguish itself from siblings like generate_flashcards or generate_study_plan, but the resource noun makes the intent unambiguous.

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 states a precondition ('Requires a connected Scholarize account'), which is useful usage context, but gives no when-to-use guidance or comparison against alternatives. An agent must infer that this is the tool for quiz requests rather than flashcard or study-plan requests.

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 only declare that this is a non-readOnly, open-world, non-idempotent, non-destructive write. The description adds genuinely useful behavior beyond that: it returns a plan summary plus a shareable link, and requires no account or email. It misses one annotation-relevant detail — since idempotentHint=false, each call presumably creates a new plan/link, which the description doesn't warn about.

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 action and artifact, followed by the return behavior and the usage trigger. Nothing repeats the schema or pads the definition.

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 present, the description correctly spells out what comes back (summary + shareable link) and removes auth concerns. Only the repeat-invocation behavior implied by idempotentHint=false is left unexplained, which is a minor gap for a two-parameter tool.

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 both parameters are already documented, including email being optional and not needed for the result. The description reinforces the flexible content of 'syllabus' (topics or a plain description) but adds no syntax, length, or formatting guidance beyond the schema, so the 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 ('Create') plus resource ('personalized week-by-week study plan') and enumerates the accepted input forms (syllabus, exam topics, freeform description). The artifact produced is clearly distinct from sibling generators like generate_flashcards or generate_quiz, so no explicit sibling callout is needed.

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 names the trigger: 'Use it when a student asks for help planning their studying or exam prep.' That is a clear usage context, though it gives no when-not guidance or points to alternative tools for adjacent needs.

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 declare readOnlyHint=false, openWorldHint=true, and idempotentHint=false, so the mutation and non-determinism profile is covered. The description contributes the genuine extra fact that no account or email is required, but it does not say whether repeated calls yield different options or how many options come back, so added value is modest.

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?

Two sentences, front-loaded with what is produced and from which inputs, followed by the usage cue. Every clause carries information; nothing is repeated from the title alone.

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 simple generation tool with a fully documented schema and no output schema, the description covers purpose, inputs, and the auth-free behavior. It stops short of describing the shape of the result (how many thesis options, whether they are labeled by essay type), which is the only real gap.

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 every parameter including email, topic, position, and essayType is already documented with an enum and example. The description echoes the topic/type/stance framing but adds no syntax, length, or format guidance beyond the schema, which is the expected baseline.

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 (generate) and resource (thesis statement options) and enumerates the inputs that shape the output: topic, essay type with its four values, and optional stance. That is enough for an agent to distinguish it from siblings like generate_quiz or generate_citation 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?

"Use it when a student needs a thesis or essay direction" gives a clear triggering context. It does not name an alternative or state when not to use it, but among the listed siblings none overlaps meaningfully with thesis generation, so the missing exclusions cost little.

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 declare readOnlyHint=true, idempotentHint=true, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description usefully adds the account-connection prerequisite, but says nothing about result format, pagination, or empty-state behavior.

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?

Two short sentences, front-loaded with the action and resource, with the prerequisite second. Nothing is wasted or buried.

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 zero-parameter read-only list tool with full annotation coverage and no output schema, the description supplies the one thing structured fields don't: the account-connection requirement. Adequate, though return-shape expectations are left unstated.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate. Baseline 4 applies since the schema is trivially complete.

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 ('List') and resource ('connected student saved flashcard sets'), which is clear enough that an agent can distinguish it from generate_flashcards. It does not explicitly name or contrast any sibling, but the list-vs-generate distinction is readable from the wording.

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?

'Requires a connected Scholarize account' is an implicit precondition that tells the agent when this tool is unusable, but there is no guidance on when to prefer it or which sibling to use instead. Minimal viable usage guidance.

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 declare readOnly, idempotent, non-destructive, and closed-world behavior, so the safety profile is fully covered. The description adds value beyond them by disclosing the connectivity precondition, which an agent must verify before calling; it says nothing about volume limits or return shape, which keeps it short of 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.

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

Two short sentences, zero waste, with the action front-loaded and the precondition following immediately. Nothing is padded or redundant.

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 zero-parameter, closed-world list tool with no output schema, the description covers what the agent needs to decide and invoke it. It could optionally note what is returned (quiz names/identifiers) and whether it is scoped to all saved quizzes or a subset, leaving a small gap.

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?

The tool takes zero parameters, so the baseline is 4 and there is no schema semantics for the description to expand upon. Nothing is missing on this dimension.

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 (List) and resource (saved quizzes) scoped to the connected student's own account in Scholarize. The resource name naturally distinguishes it from its near-twin sibling list_my_flashcards, though no sibling is named 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?

Provides one actionable prerequisite: a connected Scholarize account is required. However, it gives no when-to-use guidance relative to alternatives such as generate_quiz (create) or ask_ai_tutor, leaving that inference to the agent.

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