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

With no annotations, the description carries the behavioral disclosure burden and does so substantively: single forward pass, catalog cap of <=20 labels, ~2-5 ms per item cost, and label-with-confidence output. It does not discuss failure modes or side effects, but for a classifier this is meaningful transparency.

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 tight sentences front-load the core operation and constraint, then add cost and output details. Every clause contributes useful information with no filler or 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?

Given the output schema exists and the schema provides defaults for timeout_ms and instructions, the description is largely complete: it states what the tool does, when to use it, its constraints, cost, and output. The main gaps are catalog structure and explicit parameter guidance, but these are partially covered by the input schema.

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 adds meaning to 'catalog' (shared, <=20 labels) and 'items' (many items classified per call), but it never mentions timeout_ms or instructions, and the catalog object's structure is left to schema inference.

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: 'Classify many items against one shared catalog.' It further distinguishes itself from siblings by emphasizing batched, single-pass classification with a label limit and per-item confidence output.

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 a clear intended use case ('dedupe / triage / labelling sweep') and a cost-based rationale for choosing it ('cheaper than one LLM reasoning turn'). However, it never explicitly names sibling tools or states when not to use it, and mentioning 'triage' creates potential overlap with the sibling laya_triage.

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 full burden. It discloses latency (~10-20 ms), the nature of output (probabilities, no text generation), and a calibration caveat. It does not mention side effects or permissions, but the wording 'ask ... about a state' implies a read-only, non-destructive operation.

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?

Every sentence earns its place: purpose, output type, performance, and usage constraints are packed into a compact, front-loaded description. No filler or 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?

The tool has an output schema, so return-value detail is not required. The description covers core usage and constraints well, but the 'preset' parameter is completely undocumented in both schema and description, and 'noul' is unexplained. Given the tool's moderate complexity, this is a minor gap.

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 adds meaningful semantics for 'state' (text, email, ticket, JSON) and 'questions' (choice|score|noul, answer space per call, under 20 options). However, 'preset' and 'timeout_ms' are left unexplained, and 'noul' is undefined. This partial compensation warrants a middle score.

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 clearly identifies the tool as a decision engine for 'typed questions about a state' and enumerates supported state types. It is specific in verb and resource, though it does not explicitly contrast with sibling tools like laya_gate or laya_classify.

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 provides clear operational context: question types (choice|score|noul), output characteristics (probabilities, act/escalate signal, no text generation), and practical constraints (under ~20 choices, probabilities as hints). It does not name alternative tools or exclusion conditions, so not 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 provided, the description carries the behavioral disclosure burden. It transparently states that the tool returns specific risk probabilities and a severity level, and it notes the ~15 ms latency. It does not state explicit side effects, but as a gating/classification tool, its read-only nature is reasonably implied. It avoids contradicting anything and adds meaningful behavioral context.

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 compact and front-loaded: purpose first, then outputs/latency, then actionable threshold advice. Every sentence contributes essential information with no 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?

Given that an output schema exists, the description does not need to detail return structures. It covers the when, what, and how-to-act, leaving out only parameter details and explicit sibling differentiation. Overall, it is sufficiently complete for an agent to invoke the tool correctly in most situations.

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 for parameter meaning. It references 'untrusted text' which implies the 'text' parameter, but it never explains the 'timeout_ms' parameter, its default, or how it affects behavior. The description adds little beyond what the parameter names already imply.

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 clearly states the tool's role: a safety gate for untrusted text before it enters context. It names the specific function (returning jailbreak, prompt_injection, and sensitive_data probabilities plus a harm severity level), making its purpose unambiguous and distinct from typical tools.

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 concrete usage guidance: apply to untrusted text before it enters context, use a threshold of ~0.5-0.7, and quarantine or summarise rather than trust the raw text. It does not explicitly name alternatives or exclusions among siblings, but the context and expected workflow are clear.

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 full behavioral burden. It discloses the non-obvious side effect that probing may start the engine if needed, and explains that a `reachable: false` result surfaces the underlying error. This goes beyond a simple 'check health' statement and gives the agent a realistic behavioral model.

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 sentences deliver a dense but efficient description: the purpose and key payload are front-loaded, followed by the usage condition and error behavior. Every clause earns its place, and there is no redundant restating of the tool name 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 the empty input schemaaren't any parameters and the presence of an output schema, the description covers the essential decision context: what the tool reports, that it may start the engine, and how to interpret failures. Nothing an agent needs to call this correctly 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?

The input schema has zero parametersless, so the baseline is 4 and the description does not need to explain parameter semantics. The description's enumerated outputs indirectly clarify what the tool returns, but no parameter context is required.

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 pair ('Report and PROBE the Laya backend') and enumerates concrete outputs: reachable, executable, loaded model/family, device, CUDA-graph status, timeout, uptime, and call count. This clearly identifies the tool as a health/diagnostic probe and differentiates it from the sibling decision/routing tools just by naming its scope.

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 explicit trigger conditions: 'Use when another tool times out or returns a daemon error.' This is clear operational guidance, though it does not explicitly state when not to use the tool or name alternative tools for other situations. The signal is strong enough for an agent to select it appropriately.

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 provided, the description carries the full burden of disclosure. It does reveal the decision output ('act/escalate signal') and the dimensions considered, which is meaningful beyond what the output schema would show. But it stays silent on failure behavior, timeout semantics (relevant given timeout_ms param), and what happens when the routing is ambiguous — leaving the agent to discover these at runtime.

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 sentences, no fluff, purpose front-loaded in the first clause. Every clause earns its place — outputs are listed compactly and the usage trigger is given immediately after. Minor deduction because the structure could have folded parameter guidance into the same space without adding length.

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 core intent and use-case trigger are well covered, and the existence of an output schema relieves the description of return-format duties. But with no annotations and 0% schema coverage, the timeout parameter is entirely undocumented, and the routing criteria are described at a high level without example inputs/outputs. For a tool this central to cost control, an example of a routed result would materially improve completeness.

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, but it only implicitly references the 'task' parameter ('for a task description') and says nothing at all about timeout_ms. Neither parameter gets a format, expected value range, or example. The burden is on the description to document parameters when the schema has empty descriptions, and it fails to do so for half of them.

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 verb ('route') applied to a task description, and enumerates the concrete outputs: difficulty, model tier, tool/human-review need, and an act/escalate signal. This clearly distinguishes it from generic 'decide'/'classify' siblings, though it never names an alternative explicitly. The stated intent — cost/quality tradeoff before expensive work — makes the role unambiguous.

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 second sentence gives an explicit trigger: 'Use before firing a scheduled job or an expensive agent turn.' This is concrete and actionable. However, it offers no negative guidance — it never says when NOT to use this tool or points to a sibling (e.g., laya_gate or laya_classify) for cases where pure classification or gating is needed instead.

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 behavioral burden. It does disclose that this is a one-pass probabilistic classifier and that low confidence should trigger human escalation. However, it does not mention whether the call is read-only, what failure modes exist, or any rate/auth constraints, leaving some behavioral context implicit.

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 sentences, front-loaded with the core action, and every clause adds useful information. There is no filler or repetition 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 tool is simple and has an output schema, so the main intent, outputs, and usage are covered. But the unexplained optional timeout_ms, combined with zero annotation support, means an agent still needs to infer part of the calling contract.

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 implies the required 'text' parameter through 'message or ticket', but it never explains the optional 'timeout_ms' parameter or how it affects the call. This leaves part of the parameter surface undocumented.

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 ('Triage a message or ticket') and enumerates the exact outputs: intent, urgency, frustration, refund request, churn risk. It also clarifies it returns probabilities per aspect in a single pass, which separates it from generic classify/decide siblings 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?

It gives explicit when-to-use guidance: use it to route or prioritize before an expensive agent turn, and escalate to a human when confidence is low. It does not explicitly name alternative tools or state when not to use it, so it falls just short of 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 provided, the description carries full responsibility, and it delivers: it discloses that the response is advisory, non-blocking, schema-driven, versioned, comparable across models, and re-measurable. It also clarifies the decision should not be the sole gate for action. This is rich behavioral context beyond a simple 'routes a step.'

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 dense but tightly organized: action and timing up front, then tier definitions, then advisory caveat, then alternative routing. Every sentence contributes; no filler or 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?

Purpose, advisory nature, evaluation semantics, and alternative routing are all covered. An output schema exists, so return-value documentation is not needed. The only gap is unspecified parameter details for backend and timeout_ms, but these are minor given the rich context and existing schema.

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 adds meaning to the core 'task' parameter by describing routing dimensions (tiers, needs_tools, sensitive flags). However, it does not explain 'backend' or 'timeout_ms,' leaving those undocumented in both schema and description. Strong on the central parameter, slightly incomplete on the others.

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+resource: 'Route a step to a tier BEFORE running it,' and concretely defines the tier meanings (economy vs frontier) with behavioral attributes. It explicitly differentiates itself from the sibling laya_route by noting it is the 'measured, schema-driven one,' so an agent can distinguish the tools without opening schemas.

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 when-to-use guidance: decide which model should do the work, never to block an action, and gate on the committed eval rather than a single call. It names an alternative (laya_route) and states the condition selecting it (fixed-preset vs measured). No ambiguity remains about when this tool should be invoked.

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 provided, the description carries the full burden of behavioral disclosure. It reveals that output is limited to typed values (yes/no or closed set) to prevent instruction injection, discloses the measured accuracy (0.602 vs 0.569 baseline) and its advisory nature, and mentions the cost model (state x questions). This is exceptionally transparent about limitations and behavior.

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 yet information-dense. Every sentence adds value: purpose, output format, accuracy, advisory nature, and cost guidance are all packed into a compact paragraph. The most critical information (purpose and output type) is front-loaded, followed by performance and usage caveats. No filler or 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?

Given the tool's complexity (5 parameters, no annotations, output schema present), the description is largely complete. It explains the core behavior, output format, accuracy, and usage constraints. It omits details on optional parameters, but these have defaults and are not critical for basic usage. The output schema exists, so return values need not be described. Overall, it covers what an agent needs to call the tool correctly, with minor gaps on optional settings.

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 clearly explains the two required parameters (before and after accessibility captures) by stating 'give the accessibility capture before and after the action'. However, it does not explain the optional parameters (backend, max_lines, timeout_ms), which remain undocumented. The description adds meaning for the core parameters but leaves the optional ones unexplained.

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 clearly states the verb 'verify' and the resource 'a step from an accessibility diff', and explains the exact function: providing before/after captures and receiving typed answers about screen state. It distinguishes itself from sibling tools by focusing on verification rather than deciding, gating, or routing, and the specific input/output behavior is unambiguous.

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 explicit usage guidance: treat answers as advisory evidence with a known error rate, never as the gate that decides a step is done. It also advises asking few questions per call due to encoder cost. This clearly tells the agent when and how to use the tool, and implicitly when not to (not as a gate).

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