veritap

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

The description adds 'Free, read-only, no side effects' and explains return behavior ('what evidence would come back, and an honest answer when it cannot'). These details go beyond the annotations (readOnlyHint, idempotentHint) and do not contradict them.

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: four sentences covering purpose, safety/cost, trigger condition, and return behavior. There is no redundant content; each 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?

Given no output schema, the description explains the return value ('whether it can be corroborated... what evidence would come back'). It also covers key operational traits (free, read-only). It doesn't address asynchronous behavior or parameter interdependencies, but these are not required for a basic understanding.

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 provides full descriptions for all 9 parameters (100% coverage). The tool description adds no parameter-specific semantics, but the schema already fulfills that need, so a 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?

The description uses a specific verb and resource: 'Check whether a fact can be corroborated' and 'Returns whether it can be corroborated from sources today.' This clearly differentiates it from siblings like check_feasibility and check_physical_condition, which focus on different aspects.

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?

'Use when a step rests on something you have only inferred from text and being wrong would be expensive' gives an explicit trigger condition. However, it lacks explicit when-not-to-use or named alternative tools, which prevents 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?

Annotations already provide readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is known. The description adds valuable context beyond annotations: it declares 'Free, no auth, read-only, no side effects', explains that unsupported claims are logged and prioritized, and states 'Never errors'. This enriches the 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?

The description is front-loaded with the core purpose, followed by usage guidance and behavioral details. The second paragraph is somewhat dense but still efficient. Every sentence earns its place, and the structure aids quick comprehension.

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 (9 parameters, nested objects, no output schema), the description provides substantial context: it explains the planning use case, coverage, unsupported claim handling, and error guarantees. It does not describe the exact return response, but for a feasibility-checking tool used in planning, this is sufficient.

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% with detailed descriptions for all nine parameters, so the schema does the heavy lifting. The description adds general context (e.g., coverage of businesses, listings, objects, places) but does not clarify individual parameters beyond what the schema already provides. 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?

The description clearly states the tool's purpose: checking whether a real-world fact can be verified before committing to a paid request. It also lists covered domains (businesses, listings, objects, places). However, it does not explicitly differentiate from sibling tools like check_before_relying or confirm_before_purchase, so it stops short of a 5.

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 explicitly advises when to use the tool: whenever a task depends on a physical-world fact that cannot be confirmed, and encourages speculative use during planning. It does not mention when not to use or name alternative tools, so it lacks explicit exclusions.

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 annotations, the description adds valuable behavioral specifics: it is free, returns only what can be corroborated from sources today, and explicitly states it will say when physical inspection is required rather than dispatching someone. This goes well beyond the readOnlyHint and destructiveHint 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 compact and front-loaded, with a clear two-paragraph structure. Every sentence adds distinct value: purpose, usage condition, and behavioral limitation. No redundant or verbose phrasing.

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 9 parameters and no output schema, the description adequately covers purpose, usage, and return behavior at a high level. It could have specified the return format or parameter interplay, but the schema already handles parameter details, and the description gives enough context for an agent to invoke it appropriately.

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 100% description coverage for all 9 parameters, so the description does not need to restate them. It adds only slight contextual framing (e.g., 'condition a listing claims' relates to claim_description) but not meaningful semantic elaboration beyond 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 first sentence states a specific verb ('Check') and resource ('physical item or property') with clear scope ('stated condition, damage, or grading'). This distinguishes it from siblings like check_feasibility or confirm_before_purchase, which target different decision types.

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 an explicit when-to-use condition: 'Use when a decision depends on an item being in the condition a listing claims.' It also gives a clear exclusion—'nobody is sent to look'—implying physical inspection is not performed. However, it does not name alternative tools, so it falls short of the highest bar.

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 description adds value beyond annotations by noting the tool is 'Free, read-only, no side effects' and explaining what it returns ('what can be corroborated, what cannot, and — when it cannot — whether you could settle it yourself and how to proceed'). This complements the provided readOnlyHint and idempotentHint rather than merely repeating them.

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 two sentences, front-loaded with the core purpose and safety profile, then adds usage timing and expected return information. Every sentence earns its place with 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?

For a tool with 9 parameters, nested objects, and no output schema, the description provides the essential usage context and return behavior. It does not mention all asynchronous nuances (e.g., callback_url) but those are already documented in the schema, and the description covers the main decision-making flow sufficiently.

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 100% description coverage for all 9 parameters, including nested objects and optional fields, so the schema already documents parameter semantics thoroughly. The description does not repeat parameter details but also does not add further nuance beyond the schema, matching the baseline expected when schema coverage is high.

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 whether a listing, item, or business can be corroborated') and clearly ties the tool to purchase decisions ('before spending money', 'before any irreversible spend'). This distinguishes it from siblings like check_before_relying by emphasizing the financial/purchase context, so there is no ambiguity about what the tool does.

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 explicitly states when to use the tool: 'Use before any irreversible spend where the counterparty or the goods have only been seen online.' It gives clear usage context but does not explicitly mention when not to use it or name alternative tools, so it falls just short of the highest tier.

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 annotations (readOnly, idempotent, non-destructive), the description adds cost/auth context ('Free, no auth') and fully specifies the return format: per-step grounding status, claim type, and guidance for ungroundable steps. It also clarifies input expectations ('whole plan'). This is substantial extra behavioral disclosure.

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 concise paragraphs with front-loaded purpose. The first sentence states the core action, and subsequent sentences provide high-value usage and output information without fluff. 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 adequately describes what is returned (per-step grounding, claim type, and next steps). It also provides input guidance and safety context via annotations. For a moderately complex tool (2 params, nested array), this is 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 coverage is 100%, so the baseline is 3. The description does mention passing the whole plan, but that is more of a usage guideline than new parameter semantics. It does not add details about the 'goal' or 'steps' structures beyond what the schema already 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 title and description state a specific verb ('map') and resource ('multi-step plan', 'real-world facts'). It clearly distinguishes itself from siblings like check_feasibility or triage_unknowns by focusing on verification of unverified facts, not checking feasibility or physical conditions.

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 timing: 'call liberally during planning' and 'Pass your whole plan, including steps you have not decomposed into questions yet.' This implies it should be used early in planning, before finer-grained checks. However, it does not explicitly name alternatives or exclusions, so it falls 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?

The description goes beyond the annotations by stating 'Free, instant, read-only, no side effects' and elaborating the classification behavior, including honest routing of self-answerable items and providing price/turnaround for verifiable ones. This complements the readOnlyHint, openWorldHint, idempotentHint, and destructiveHint annotations without contradiction.

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 a one-sentence summary and then expands into the classification behavior. Every sentence contributes, and the two-paragraph structure is efficient and readable.

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?

While there is no output schema, the description communicates the three classification outcomes (answerable with source, verifiable with price/turnaround, not determinable with advice), which gives a solid picture of the response. The tool's simplicity and thorough annotations mean the description covers all essential context, though exact output formatting is not specified.

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 100% description coverage for all three parameters, so the baseline is 3. The tool description's mention of batching 'every uncertainty at once' mirrors the schema description for 'unknowns' and does not add additional syntax or format details, so no bonus beyond the baseline.

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 triages uncertainties into answerable, verifiable, or not determinable categories, with a specific verb ('triage') and resource (uncertainties). It distinguishes from siblings by emphasizing read-only, free, and instant, and by describing an honest routing mechanism that other tools likely don't have.

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 explicitly advises to 'call liberally during planning' and to 'dump every uncertainty at once, mid-reasoning, before deciding which are worth chasing,' providing clear when-to-use guidance. It does not explicitly name alternative tools or state when not to use, but the planning context is clear.

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