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

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly states 'This is advisory -- it returns a recommendation, not enforcement,' which is a key behavioral trait. It also lists the output fields, though it does not explicitly say the tool does not execute the command; the advisory note strongly implies this.

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 well-structured and front-loaded: purpose first, then usage directive, then a NOTE, then parameter details, then return information. Every section serves a purpose, and the length is justified by the need to document parameters given 0% schema coverage.

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?

This is a 5-parameter tool with 0% schema coverage and an existing output schema. The description covers all parameters, defaults, the advisory nature, and the return fields. Given the output schema exists, the description is complete enough for an agent to call the tool 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 0%, so the description must compensate. It explains every parameter: command and goal are required, workspace is optional context, and the two thresholds have defaults and semantic meaning. This adds substantial value beyond the raw schema types.

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: 'Check if a command or action is safe before running it.' It clearly states what the tool does and mentions the return type (risk probabilities and recommended action). It does not explicitly differentiate from sibling tools like fast_judge or fast_verify, but the 'before running' framing gives reasonable distinction.

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?

Includes an explicit directive: 'Call this BEFORE executing shell commands, file modifications, or API calls.' This is clear context for when to use the tool. However, it does not mention when not to use it or name alternative tools, so it stops short of a full 5.

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?

No annotations are provided, so the description carries the full behavioral burden. It discloses the output shape (JSON with choice, confidence, probabilities, is_confident) and defines the confidence_floor behavior. It does not discuss side effects, failure modes, or edge cases, but for a selection tool this is reasonably transparent.

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 concise and well-organized: purpose statement first, then return behavior, then usage guidance, then Args, then Returns. Each sentence earns its place, and the key usage instruction is front-loaded. The only minor redundancy is restating the return fields, but it's not wasteful.

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 4 parameters, nested options, and an output schema, the description gives enough to call it correctly: parameter semantics, confidence threshold, and output structure. It doesn't specify what happens when options tie or whether the choice key is guaranteed to be one of the option keys, but such edge details are minor. Overall, the description is nearly complete.

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 0%, yet the description's Args section fully explains all four parameters: question ('What to decide'), options ('Dict mapping candidate keys to descriptions (at least 2 options)'), context ('Optional context or state'), and confidence_floor with its default. This completely compensates for the absent schema descriptions.

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 'Instantly select the best option from a set of candidates,' which clearly states the verb and resource. It adds return details (choice, confidence, probabilities). However, it never explicitly differentiates from sibling tools like fast_guard, fast_verify, or fast_score, though the selection-focused purpose is distinct enough.

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 explicit usage context: 'Call this when you need to pick one item from a known set without slow deliberation.' This tells an agent when to use it, but it doesn't mention when not to use it or name alternative tools. The guidance is clear but lacks exclusions or contrast with siblings.

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 no annotations, the description must carry behavioral disclosure, and it does add useful context by explaining that the tool returns a score, probability distribution, and confidence, and that confidence_floor is a threshold. It does not address side effects, failure modes, or nondeterminism, but for a stateless rating tool the disclosed behavior is not dangerously incomplete.

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?

Structured into purpose, usage, args, and returns with no filler; the main use case is front-loaded in the first line and each section 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?

Four parameters are fully documented, the return shape is explicitly stated, and an output schema exists, so the agent has enough to invoke the tool correctly. It loses a point only because the relationship to fast_judge/fast_verify and the precise effect of confidence_floor on is_confident are left implicit.

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 0%, so the description must compensate, and it does. Each parameter is explained in plain terms: question gets an example, levels gets an ordering constraint and minimum length, content gets accepted types, and confidence_floor gets a default and purpose. This goes well beyond the bare 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 first sentence states a specific action ('Rate content along a defined scale with ordered levels') and lists concrete use cases (severity, quality, relevance, complexity), so an agent knows what the tool does. It does not explicitly contrast with siblings such as fast_judge or fast_verify, so it misses the top marker for sibling differentiation.

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 says explicitly to 'Call this for severity, quality, relevance, complexity, or any custom rating', giving clear criteria for when to use it. It does not name alternatives, exclusions, or conditions for using fast_judge/fast_verify, so it lacks the when-not/alternative guidance needed for a 5.

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 no annotations, the description carries the transparency burden and does well: it explains the probability output, the return fields, and optional yes/no clarification parameters. It does not discuss edge cases or limitations, but the read-only, input-output nature of the tool is clearly conveyed.

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 well-organized with a one-sentence summary, a 'Returns' line, and a compact Args list. Every sentence adds useful information and there is no redundancy or filler.

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 definition covers inputs, outputs, use cases, and optional parameters, which is solid for a four-parameter tool with no annotations. It could additionally explain how to handle insufficient/ambiguous evidence or mention any limitations, but nothing critical is missing for invoking the tool 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 0%, so the description must define parameters itself. It provides meaningful explanations for all four parameters: statement, evidence, yes_means, and no_means. This fully compensates for the bare 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 uses a specific verb ('check') and identifies the resource (whether a condition is true or goal met), with clear use cases listed. It clearly describes what the tool does but does not explicitly contrast it with sibling tools like fast_judge or fast_score, so it misses the full sibling-differentiation marker.

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 states explicit call contexts: 'Call this to verify goal completion, test outputs, status checks, and loop detection.' This gives clear when-to-use guidance, though it does not mention when not to use it or name alternative sibling tools.

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