Quant Daily

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

Adds substantial behavior beyond the annotations: the question is identical for every conversation and pre-validated for a single correct answer, the answer and explanation are deliberately withheld, and attempt counting is per-conversation. This also explains why readOnlyHint=false and idempotentHint=false apply — calling it has a side effect on attempt state.

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?

Four short sentences, front-loaded with the core purpose, then returns, then constraints. Minor redundancy: the 'English only; lang hi is rejected' clause restates what the lang schema description already says, costing a little space.

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 carries the return-value burden and does so: it names the returned fields (exam, difficulty, expected time) and explicitly lists what is omitted. Combined with the language and attempt-counting rules, an agent has everything needed to call 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 coverage is 100%, so both lang and attemptId are already fully documented in the schema, including the same 'per conversation, not per person' and 'hi is rejected' phrasing that appears in the description. The description adds no syntax, format, or lifecycle detail beyond the schema, so the baseline of 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?

Specific verb and resource ('Fetch today's Quant Daily drill'), scoped to GRE/GMAT quant, with an explicit statement of what is returned (exam, difficulty, expected time) and what is not (answer, worked explanation). It is clearly separable from get_practice_drill and get_drill_hint by implication, though it never names those siblings directly.

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 concrete usage constraints: English only, 'hi' is rejected, attemptId must be reused across calls in a conversation, and attempts are counted per conversation rather than per person. It stops short of explicitly stating when to prefer get_practice_drill or get_drill_hint over this tool, so the alternative-condition guidance is inferred rather than stated.

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 and idempotentHint=false, and the description adds real context that explains why: attempts are counted per conversation, so repeat calls have a cost. It also discloses the deliberate output limit (no option, no worked explanation), which the 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 short, front-loaded sentences with no filler; the key constraint (no answer reveal) comes before the bookkeeping note. The final sentence largely echoes the schema's attemptId description, a 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?

With no output schema, the description usefully characterizes what the response will and will not contain (first step only, not the option or explanation). The attempt-counting cost is disclosed. Only the exact format of the returned hint is left unstated, which is acceptable for a small 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 the schema already documents drill values, the attemptId conversation id, and the lang enum. The description restates the per-conversation attempt semantics but adds no new parameter detail, so 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: 'ask for the first step on a Quant Daily question', and scopes it with 'Name the drill type'. This is clearly distinguishable from get_daily_drill and submit_drill_answer, though it never names those siblings 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?

Usage is implied ('ask for the first step') and bounded by what it will not return, but there is no explicit when-to-use statement or routing versus get_daily_drill and get_practice_drill. The agent must infer that this is the tool to reach for after already having an attemptId.

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 mark the call non-read-only and non-idempotent; the description supplies the reason by disclosing the per-conversation quota, which is exactly the behavior an agent needs to avoid wasting calls. It also asserts the question is 'checked to have one correct answer' and that results are excluded from ranking. It does not say what happens when the quota is exhausted.

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 the action before qualifiers, with no filler. The quota sentence and the sibling-exclusion sentence both earn their place, though the phrasing is slightly telegraphic.

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 tool with no output schema, the description covers the key constraints: quota, language, ranking exclusion, and question validity. It could say more about what the opened question actually returns (stem, options, an id), but the essential calling context is present.

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 both parameters are already documented in structured form, and the description only echoes the existing lang constraint ('English only; lang hi is rejected'). The attemptId-by-conversation semantics are handled entirely by the schema, so the description adds no meaning beyond it.

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 and resource ('Open one extra Quant Daily practice question') and immediately scopes it against siblings: 'These are not today's shared drill and they are not in the attempt ranking.' An agent can distinguish it from get_daily_drill without opening the 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?

It makes clear this is the extra-practice path, not the shared daily drill, and states a concrete usage budget ('2 practice questions today, the anonymous allowance'). It stops short of explicitly naming get_daily_drill as the alternative for the shared drill, leaving that routing to be inferred from the sibling's name.

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 indicate a non-idempotent, non-destructive write, and the description goes well beyond them: a wrong guess does not reveal the answer, attempts are per conversation not per person, completion returns a Verified answer plus worked explanation, and a correct answer appends a practice link. It also pre-empts misreading of the comparison line (attempts, not time; anonymous; not the website leaderboard; non-prod conversations excluded).

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 return value, then layered outward into edge behaviors. A few clauses (the dev/staging/test exclusion, the leaderboard disclaimer) are dense but each removes a likely misinterpretation, so it is only mildly overlong.

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 carries the full burden of describing returns and does so thoroughly: verdict, attempts remaining, on-completion Verified answer and explanation, comparison line, and practice link. Nothing an agent needs to call this correctly or interpret the response 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 every parameter including the lang enum and the "send the id, not the option text" caveat is already documented in the schema. The description adds only an indirect restatement of attemptId semantics ("three attempts per conversation, not per person"), 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?

"Submit one option id for a Quant Daily drill" is a precise verb+resource, and the description immediately states what comes back (right/wrong plus attempts remaining). It implicitly separates itself from get_daily_drill/get_drill_hint (this is the submission step) and from practice drills via the drill parameter, but never names a sibling outright.

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 drill parameter is explained as either "daily" (today's shared drill) or a practice id returned by get_practice_drill, which gives the agent a concrete routing rule between the two drill families. The attempt budget ("Three attempts per conversation") tells the agent when a further call is still possible, though there is no explicit "do not call this before/after X" instruction.

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