BetterChess

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

With readOnlyHint=true already covering safety, the description adds substantial behavioral context: it reports what the opponent would play, explains that `considering` returns the refutation line, and warns that losing moves usually fall outside top candidates. This is exactly the kind of non-obvious behavior an agent needs, and nothing here contradicts 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?

Three dense sentences, front-loaded with the main purpose and ending with the actionable `considering` use case. The 'quiet and merely looking quiet' phrasing adds color and some explanatory value, but is slightly more ornamental than strictly necessary.

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 return values well: candidate moves, scores, checkable facts, opponent reply, and refutation lines. It omits a few correctness details—there is no explicit statement that exactly one of fen/pgn/moves is needed despite zero required parameters, and engine score units/format are not described.

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 goes beyond the schema by linking the three position input parameters as alternatives and by explaining the non-obvious meaning of `considering` (returning the refutation line, not just an evaluation). Minor parameter semantics like multipv interaction and score format are left to the schema/defaults.

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 leads with a specific verb and resource—'Returns an engine evaluation of a chess position'—and enumerates exact outputs: candidate moves, scores, side to move, check status, undefended pieces, and material balance. It is not a tautology and clearly surpasses the generic title, but it never names or contrasts the sibling tools, so explicit sibling differentiation is missing.

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 input guidance ('Accepts a FEN, a PGN, or a list of SAN moves') and a targeted use case for `considering`, even explaining when asking directly is the only way to expose a losing move. However, it never states when to prefer this tool over chess_attacks/chess_review or when not to use it, leaving alternative selection implied rather than explicit.

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 readOnlyHint=true, and the description adds meaningful behavioral detail: unoccupied squares return an empty list, output includes piece type and colour, and the accepted position formats are disclosed. No contradiction with the read-only annotation exists.

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 tightly written sentences front-load the core result and the key edge case, then list accepted input formats. Every sentence earns its place and there is no filler or redundant restatement of the tool name.

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 is complete for a simple computation tool: it explains the return value and the empty-list case, which is especially important because there is no output schema. It names all three position input types, though it does not specify what happens if multiple position arguments are supplied or what the default starting position is.

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 adds context by naming FEN, PGN, and SAN moves as the position inputs and noting that SAN moves begin from the starting position. However, 'square' semantics are left to the schema's example, and the description does not significantly deepen parameter understanding.

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—'Returns the exact list of squares attacked'—and names the resource: the piece standing on a given square. It also includes return details (piece type and colour) and edge-case behavior, making its purpose unmistakable and distinct from the broader chess_analyse and chess_review siblings.

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 usage: use this when you need the squares a particular piece attacks. It also states the accepted input formats (FEN, PGN, or SAN moves), which helps with input preparation. However, it never explicitly compares this tool to chess_analyse or chess_review, nor gives when-not-to-use 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?

Beyond the readOnlyHint and openWorldHint annotations, the description discloses substantial behavioral traits: the threshold default, the 60-ply truncation, the exact per-entry output composition, and the accepted input formats and colour filter. These details are not available in the annotations and are highly relevant to invoking the tool correctly. The description is fully consistent with 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 arranged efficiently: core behavior first, then return format, then input and limitation details. It is three sentences with no filler and no unnecessary repetition of schema content. Every clause contributes new, useful information for an agent.

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 fully accounts for return values by listing every field in each entry. It also covers both accepted input representations, optional colour filtering, the threshold behavior, and the truncation limit. This is a complete picture for a read-only analysis 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?

The schema already provides 100% parameter coverage with descriptions for pgn, moves, colour, and threshold, so the description does not need to re-document them. The description adds a little context, such as the input alternatives and colour filtering, but mostly restates behavior rather than clarifying individual parameter semantics. This matches the baseline for high schema coverage.

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 contains a specific verb and resource ('Replays a finished game... returns the moves where the evaluation swung'), which makes the tool's purpose exact and easily distinguishable from the sibling tools. It also enumerates the returned fields, so an agent knows precisely what 'review' produces without needing 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?

The description provides no guidance on when to choose chess_review over the sibling tools chess_analyse or chess_attacks. It neither names alternatives nor states exclusions, leaving the agent to infer usage solely from the task wording. This is a clear gap given the sibling list is available for routing.

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