DeducePuzzles

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

Goes well past the annotations (readOnlyHint=false, idempotentHint=false) by disclosing that starting stores an anonymous round, that attempts are counted per conversation rather than per person, that playerToken maintains a streak but is not an account or website streak, and that starting does not sign the user into the website. These are state-mutation and identity semantics that no structured field surfaces.

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 trigger and return value, then layered exclusions and lifecycle notes. It is long — the exclusion list is a dense enumeration and a couple of sentences pack multiple clauses — but nearly every clause carries actionable information rather than repetition.

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 covers the essentials: what is returned (single-solution verified puzzle, medium difficulty, one of the listed categories) and the round/streak tokens. What it does not characterize is the puzzle's presentation format, so an agent still learns the shape of the payload only after calling.

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 lifecycle meaning: attemptId originates from this tool's own return value and must be replayed on every later call, and playerToken is optional (omit to start fresh). It stops short of restating the enum mapping, which the schema already handles well.

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 ('play today's DeducePuzzles board or a daily bank-exam arrangement puzzle') and scopes exactly what is returned: a verified single-solution medium-difficulty puzzle from a daily rotation of listed puzzle families. It is trivially distinguishable from get_hint and submit_attempt, which act on a round rather than starting one.

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 positive triggers (daily board, bank-exam arrangement puzzle, optional kind), an explicit mismatch behavior ('reports that limitation without starting a round'), and a long exclusion list covering syllogism, quant, GA, billing, user-supplied puzzles, and real-world event seating. The split between 'omit to start' and 'pass attemptId on later calls' also routes the agent within the round lifecycle.

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?

Adds real context beyond the annotations: it discloses that calls are metered ("Attempts are counted per conversation, not per person"), which explains why readOnlyHint=false on an otherwise lookup-shaped tool — each hint consumes an attempt. It also discloses the answer's disclosure boundary (no person/seat/floor/rank). It stops short of saying what happens when attempts are exhausted or whether a hint always costs one.

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 usage trigger, then output scope, then exclusions — a sensible order with no filler. The final sentence about per-conversation attempt counting partially duplicates the attemptId schema description, which is minor redundancy rather than bloat.

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 2-parameter, annotation-covered tool with no output schema, the description covers trigger, output granularity, exclusions, and metering. Remaining gaps (attempt limits, cost per call, behavior on exhaustion) are modest but would matter to an agent managing a limited hint budget.

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 attemptId and playerToken are already fully documented, including the per-conversation counting rule. The description's mention of attempt counting restates the schema rather than adding syntax, format, or edge-case guidance. 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?

Names a specific verb and resource ("get a hint" on "today's DeducePuzzles board") and pins down the exact output shape: "Names one clue to re-read, by number only." It further bounds the answer by saying it "Does not reveal a person, a seat, a floor, or a rank," so an agent knows precisely what it will and won't get back — clearly distinct from get_daily_puzzle (fetch the board) and submit_attempt (submit an answer).

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 trigger ("Use this when the user asks for a hint on today's DeducePuzzles board") plus an explicit when-not ("Do not use for a solution or a walkthrough"). Both the positive and negative conditions are stated, leaving little to inference about routing.

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?

With annotations only marking it non-read-only and non-idempotent, the description carries the real behavior: wrong guesses reveal nothing about which clues broke, the solution appears only after the round finishes, percentile has four stated gating conditions and several suppression cases, and attempts are per-conversation. This is exactly the context an agent cannot get from the schema.

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, then the result semantics, with no filler sentences. The percentile clause is dense but every condition stated materially affects how the agent reports the result.

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?

No output schema exists, yet the description fully describes the return surface: correct/incorrect, attempts remaining, round-finished flag, solution exposure, percentile and placement presence. Nothing an agent needs to interpret or relay the result 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 the description largely restates what the schema already says (attemptId is per-conversation, arrangement ordering is question-driven). It adds no syntax or format detail 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 and object (grades one arrangement for today's DeducePuzzles board) and enumerates the supported board types, making it clearly distinct from get_daily_puzzle (serves the puzzle) and get_hint (gives a clue).

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 submits an order for today's ... board') and an explicit exclusion ('Do not use to grade a puzzle this server did not serve'), plus the implicit prerequisite that the attemptId comes from get_daily_puzzle.

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