BetterChess

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

Annotations already include readOnlyHint=true, so the read-only nature is covered. The description adds valuable non-obvious behavioral detail beyond the annotations: it reports what the opponent would play, and it explains that a losing move may not appear in the top candidates, so direct probing with `considering` is needed. This is meaningful behavioral disclosure without contradicting the annotations.

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 front-loaded with the core purpose and then builds with high-value details about input formats, opponent replies, and the `considering` parameter. Every sentence adds distinct information, and there is no filler or repetition of the title or schema.

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?

Given there is no output schema, the description compensates by enumerating the return contents: engine evaluation, candidate moves with scores, side to move, check status, undefended pieces and attackers, material balance, and opponent's best reply. It also covers all input variants and the special `considering` behavior, making the tool effectively callable without missing critical 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%, so the baseline is 3. The description adds extra semantics for the `considering` parameter by explaining what it returns ('what that move actually walks into') and why it is necessary, which goes beyond the schema's one-line description. It also clarifies the input formats (FEN, PGN, or SAN moves from the start), reinforcing 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 states a specific outcome: 'Returns an engine evaluation of a chess position' and enumerates the concrete contents — candidate moves, scores, check facts, material balance. This clearly differentiates it from siblings like chess_attacks and chess_review by focusing on engine evaluation rather than raw attack detection or review.

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 gives useful contextual usage guidance, such as 'Pass considering with a move you are thinking of playing' and 'the difference between a position being quiet and merely looking quiet.' However, it never explicitly says when to choose this tool over chess_attacks or chess_review, nor does it mention any alternative or exclusion conditions.

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 annotations already declare readOnlyHint=true, and the description adds meaningful behavior beyond that: the exact empty-list behavior for unoccupied squares, the output including piece type and colour, and the supported input formats. It does not contradict the annotations, though it could further clarify whether 'attacked' includes squares occupied by friendly pieces or only legal captures in the strict chess sense.

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 with no filler. The primary behavior is front-loaded, the unoccupied-square edge case is stated, and the input alternatives are summarized compactly. 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?

The description covers return content, an edge case, and input formats, but it does not explicitly state that exactly one of fen/pgn/moves is required alongside square. Since the schema marks all three as optional and only square is required, an agent could attempt an invalid call with just a square. The lack of an output schema also makes a slightly more explicit return-format statement valuable.

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 four parameters. The description repeats the FEN/PGN/SAN input options but does not add substantial new meaning beyond what the schema's property descriptions provide, such as the constraint that at least one position source must be supplied.

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 ('Returns') and names the exact resource: the list of squares attacked by a piece on a given square, plus the piece's type and colour. It is clearly distinct from the broader siblings chess_analyse and chess_review because it targets a precise, narrow computation.

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 makes the tool's domain obvious: call it when you need the squares a particular piece attacks. However, it never explicitly contrasts this with the sibling tools or states when not to use it, leaving the when-to-use decision largely implicit.

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 annotations only declare readOnlyHint=true, and the description adds substantive behavior beyond that: engine replay, threshold default of 1.5 pawns, output fields per entry, supported inputs, colour filtering, and 60-ply truncation. These details make the tool's behavior predictable without contradicting the read-only annotation.

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 three sentences with no fluff. It front-loads the core purpose, then packs necessary operational details into the remaining sentences. 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?

With no output schema, the description takes on the burden of explaining return values, and it does: each entry's fields are enumerated. It also covers accepted inputs, configuration options, default behavior, and truncation, making the tool self-contained for an agent to use 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 the baseline is 3, but the description adds real semantic value: it clarifies that pgn and moves are alternatives ('or SAN moves'), explains the colour filter, and states the default threshold value of 1.5 pawns. This goes beyond what the schema alone 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 uses a specific verb and resource: it replays a finished game and returns moves where the engine evaluation swung by a threshold. The 'turning points' concept clearly distinguishes this from the sibling tools chess_analyse and chess_attacks, even without naming 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?

The description provides clear context for when to use the tool: after a game is finished, when you want engine-identified turning points based on evaluation swings. It mentions input options, colour filtering, and the 60-ply truncation, but it does not explicitly name alternatives or say when not to use this tool.

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