Straelo Relay

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

With no annotations provided, the description carries the full disclosure burden. It genuinely adds behavioral context: 'read-only' (no state mutation), 'normalized result' (output shape), and 'without managing an RPC provider' (operational trait). But it is silent on failure modes—reverted calls, malformed calldata, network errors—and on the exact form of the normalized result, which matters for a contract-call tool.

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?

A single front-loaded sentence with zero filler. The key action, scope, and the distinctive promises (read-only, normalized, no RPC management) all appear immediately and economically. Every clause 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 there is no output schema and no annotations, the description must carry substantial weight. It covers core purpose and key behavioral traits well, but leaves significant gaps for a blockchain-call tool: how calldata should be ABI-encoded, the shape of the 'normalized result', and error/revert behavior. An agent would likely need to probe or guess these details.

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 only 33% (only 'data' is described as 'Hexadecimal EVM calldata'). The description must compensate but does not: 'Ethereum or Base' merely echoes the chain enum, and neither contract_address (address format, checksumming) nor data (ABI-encoding requirements) gains any meaning beyond the schema. Meaningful parameter gaps remain.

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?

States a specific verb ('Execute'), a precise resource ('read-only EVM smart contract call'), and a scoped target ('on Ethereum or Base'). It also discloses the distinguishing outcome ('return the normalized result'). The sibling set is entirely in unrelated domains (DNS, email, search, web), so this tool is unambiguous by contrast.

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 phrase 'without managing an RPC provider' gives situational context that implies when this tool is useful, and 'read-only' implicitly restricts it to query-style calls rather than state-changing transactions. However, it never states explicit when-to-use vs. when-not-to conditions, nor does it name any alternative (there is no EVM sibling to route to, so the exclusion is unstated).

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 burden. 'Inspect' implies a read-only operation, but the description does not explicitly state that it is safe, non-mutating, or what happens on invalid domains. It lacks any disclosure about side effects, authentication, or rate limits.

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 a single, front-loaded sentence that states the purpose directly without any wasted words. It is concise and structured effectively for 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?

For a simple one-parameter read tool with no output schema, the description adequately covers the primary purpose. It does not specify the response format or error behavior, but these are not essential given the simplicity and lack of an output 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?

The schema description covers 100% of parameters, with 'domain' described as 'Public domain name.' The tool description adds no additional semantics beyond that, such as format examples or constraints, so it does not enhance 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 description uses a specific verb 'Inspect' and lists the exact resources (DNS records, mail configuration, SPF, DMARC) for a public domain. It clearly distinguishes itself from siblings like domain_health or email_validator_basic by its specific focus, even though it doesn't name 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 implies usage for anyone needing DNS/mail/SPF/DMARC data, but it does not explicitly state when to use this tool over alternatives or when not to use it. No exclusions or alternative references are provided, leaving selection largely to inference.

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 of behavioral disclosure. It clearly lists the checks performed, which is meaningful behavioral context. It does not mention failure modes, response format, or rate limits, but for a read-only health check the disclosed scope 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?

One sentence, front-loaded with the action, and every listed item adds value. There is no redundant or filler content.

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 single-parameter tool with no output schema, the description is mostly complete: it states what is checked and that it is done in one request. It could be more complete by mentioning the nature of the response, but the low complexity and clear scope make the gap minor.

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 the single 'domain' parameter. The description adds only the word 'public' and does not provide additional semantic detail beyond what the schema states.

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') with a clear resource ('public domain') and enumerates the exact dimensions checked: DNS, HTTP, HTTPS, redirects, TLS certificate health, and response latency. This distinguishes it from siblings like dns_intelligence, which focuses only on DNS.

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 phrase 'in one request' implies this tool is for consolidated health checks, but the description does not explicitly state when to use it versus alternatives such as dns_intelligence or web_intelligence. No exclusions or routing guidance are provided.

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 of disclosure. It clearly states the scope (syntax, domain, MX) and the absence of SMTP verification, which is a behavioral limitation. However, it doesn't mention return format or error behavior, so it is not fully transparent but sufficiently so for a simple validation tool.

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?

A single sentence that front-loads the purpose and includes a crucial limitation. Zero wasted words; every clause adds information.

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 one-parameter validation tool with no output schema, the description is adequate. It tells the agent what it validates and what it doesn't. It doesn't specify the return type, but for a simple validator the result is likely boolean/status; this is a minor gap given the tool's simplicity.

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% and the schema description already says 'Email address for syntax, domain and MX validation.' The tool description adds no new parameter-level detail beyond that. Baseline 3 is appropriate since the schema fully covers the parameter.

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 the specific verb 'Validate' with the resource 'email', and enumerates exactly what is validated (syntax, domain, MX records). It also explicitly distinguishes this from SMTP mailbox verification, so an agent can clearly tell it apart from any similar-sounding 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 phrase 'for basic automated checks' gives context on when to use it, and the exclusion 'without SMTP mailbox verification' tells the agent what this tool does NOT do, implying when a more thorough verification would be needed. It doesn't name alternatives, but the limitation is 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?

With no annotations, the description carries the full behavioral burden. It discloses that the tool performs live web research, synthesizes multiple sources, and returns cited URLs, which is meaningful beyond the tool's name. However, it does not mention potential limitations such as response delays or situations where no sources can be found.

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 a single, well-structured sentence that starts with the core action, then adds the method and output detail. Every part is informative 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 tool has one simple parameter, no output schema, and no annotations, so the description must cover the essentials. It states the input type implicitly ('question'), the research action, and the cited-URL output. It is complete enough for typical use, though it does not explicitly describe the full response structure.

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 parameter semantics are already fully documented in the schema. The description does not add further guidance about the question format beyond what the schema states, which is acceptable given the baseline for full 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 states a specific action ('Answer a question') tied to a clear method ('current web research by synthesizing evidence from multiple sources with cited URLs'). This clearly differentiates it from sibling search tools that return raw results, such as search_read or search_extract.

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 the tool is for research-backed synthesized answers rather than raw search output, but it does not explicitly state when to prefer this over alternatives or provide exclusions. The use case is inferable from the wording and sibling names, but not directly stated.

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 itself must disclose behavior. It does state that the tool queries multiple live sources and returns evidence plus source URLs, which is useful. It omits details like result counts, rate limits, or treatment of conflicting claims, but the core behavior is disclosed.

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?

A single front-loaded sentence carries the entire meaning with no filler or redundant restatement of the tool name. It is appropriately sized for a one-parameter tool.

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 simple one-parameter tool the core behavior and return type are stated, which is barely adequate. However, without an output schema or annotations and with several similar sibling tools, the description leaves gaps around query format and evidence structure that an agent needs to invoke it confidently.

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 0%, so the description needs to clarify the query parameter, but it only implies that 'query' is the search string. No guidance is provided on formatting, supported operators, or whether URLs or domains are acceptable inputs.

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 names a specific operation ('Search multiple live web sources') and a distinctive output ('structured factual claims with supporting evidence and source URLs'). This distinguishes search_evidence from sibling search tools like search_read and search_extract, which are not described as returning evidence-backed claims.

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?

No guidance is given for when to choose this tool over search_read, search_extract, research_answer, or web_intelligence. The description only states what it does; there is no when-to-use, when-not-to-use, or alternative-routing context.

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 present, so the description must carry the full behavioral burden. It adds 'live web' and 'in one request', but says nothing about result limits, missing-field behavior, rate limits, or the fact that this is a read-only network 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?

A single compact sentence with no filler and the core idea front-loaded. It is easy to scan, though more implementation detail could make it valuable without bloating it.

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 and no annotations, a tool that performs extraction should say what the response looks like or how missing fields are handled. The one-line description leaves those expectations undefined.

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%, and the description only echoes that 'fields' contain structured fields without explaining query syntax or enumerating/describing the allowed field values. The schema itself carries the real parameter meaning.

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 names a concrete action (search + extract) and a resource (live web / relevant pages), and the 'one request' phrasing hints at a combined operation. It does not explicitly position it against siblings such as search_read or search_evidence, so 4 rather than 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 implies the natural use case: the agent should call this when the user wants both a web search and field-level extraction in a single request. It includes no when-not or alternative routing clues, leaving the agent to infer when to prefer search_read or search_evidence.

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 mentions it's a 'paid request', which is useful cost context, and it says 'one request' implying bundling. However, without annotations, it doesn't disclose what 'clean readable content' includes/excludes, whether it returns multiple results, or what failure modes exist (e.g., no results, paywalled pages).

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?

A single, front-loaded sentence that efficiently communicates the tool's combined value proposition: search + content retrieval + cost model. Every phrase 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?

For a one-parameter tool with full schema coverage, the description is functional but minimal. It doesn't clarify what 'clean readable content' means in practice, whether a single page or multiple are returned, or any limitations—context that would help an agent set expectations but isn't strictly required to invoke the 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?

Schema coverage is 100% with a single query parameter that already has a description. The tool description doesn't add much beyond what the schema provides, but with only one parameter, the agent has enough information to invoke it correctly.

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 ('Search') and resource ('the live web'), and specifies the additional behavior of retrieving 'clean readable content' from relevant pages. It clearly distinguishes itself from sibling tools like search_evidence or url_clean_content by combining search and content extraction.

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 clearly implies when to use it: when an agent needs both live web search and readable content in a single paid request. It doesn't explicitly mention alternatives or exclusions, but it differentiates by bundling search+read, which helps routing among 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It discloses that the request is paid, which is a meaningful behavioral trait, and lists the data returned (status, classification, selector, gas, logs, RPC evidence). It implies a read-only retrieval, but does not discuss idempotency, rate limits, auth, or error behavior. The disclosure is partial, hence a mid-range score.

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 a single sentence that is front-loaded with the core action ('Retrieve a Base or Ethereum transaction and receipt in one paid request') and then enumerates the return attributes. It is efficient and contains no filler, though it is slightly dense with a long list of features. Overall it 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?

For a retrieval tool with two parameters, the description provides a solid overview of what is returned (deterministic status, classification, selector, gas cost, logs, raw RPC evidence). It notes the paid nature and the chain range. It does not cover failure/error cases or the exact output structure, but the core information an agent needs to decide whether this tool fits the task is present.

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 low (only tx_hash has a description). The description compensates by explicitly naming the supported chains ('Base or Ethereum') and implying the tx_hash is the identifier for the transaction. It also explains that the tool returns a receipt, linking parameter purpose to the output context. This adds meaning beyond the raw schema, though tx_hash semantics could be more explicit.

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 names a specific verb and resource: 'Retrieve a Base or Ethereum transaction and receipt in one paid request.' It clearly differentiates the tool's scope from most sibling tools (which cover DNS, email, web content), though it doesn't explicitly call out a sibling alternative. The extra qualifiers (deterministic status, classification, method selector, gas cost, logs, raw RPC evidence) make the purpose precise.

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?

There is no guidance on when to use this tool versus alternatives. The description mentions 'paid request' but does not explain prerequisites, chain-specific considerations, or situations where another sibling tool (e.g., chain_contract_call) would be more appropriate. No exclusions or conditions are given.

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 burden. It discloses that it extracts 'readable webpage text' and removes boilerplate, and the output is presumably plain text. However, it doesn't disclose what happens to non-HTML content (e.g., PDFs), or whether the tool handles redirects or requires a valid public URL. There's no contradiction, but it lacks depth on edge cases. Since it's a read-only extraction with a simple contract, a 3 is reasonable.

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 a single sentence, tightly packed with purpose and context. It front-loads the key action ('Extract clean readable webpage text') and includes the target audience, making it efficient and clear. No redundancy or fluff; every phrase 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 tool is simple with one parameter, and the absence of an output schema is acceptable since the output is implied (plain text). The description covers the primary use case and the public URL constraint. However, it doesn't mention error handling (e.g., invalid URL, non-parseable content) or the exact output format (e.g., markdown). Given the tool's simplicity, that's a mild gap. A 4 is appropriate.

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 parameter semantics are already fully documented. The description adds value by implying the URL must be public HTTP(S) and the intention is content extraction beyond the schema. With full coverage, the baseline is 3, but the description's mention of 'public' and 'webpage' gives extra context that aids agent selection, so a 4 is justified.

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 defines the action: extract clean readable webpage text from a URL. It specifies the resource (webpage text) and the purpose (LLM-ready research or RAG ingestion), distinguishing it from siblings like web_intelligence (likely broader web analysis) and search tools. It also mentions removing boilerplate, which clarifies its niche. However, it doesn't explicitly name a sibling to contrast with, but the verb and resource are specific 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 mentions 'public URL' and states the extraction is for research or RAG ingestion, implying when to use. But it doesn't explicitly say when not to use it or mention alternatives. Sibling tools like web_intelligence or search_read could be alternatives for similar tasks, but no direct guidance is given. The public URL constraint is a clear usage condition, but lack of exclusions or alternatives yields a 3.

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 burden of behavioral disclosure. It states what it produces but does not disclose side effects, read-only nature, required permissions, rate limits, or any potential limitations. The behavior is only implied by 'investigate' and 'produce'.

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 a single sentence that front-loads the action and resource, then efficiently enumerates the output components. It is concise and information-dense, with no filler or unnecessary elaboration.

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 2-parameter tool with full schema coverage and no output schema, the description provides a reasonable overview of the expected output. It lists the key data points produced, which is sufficient for an agent to understand the tool's role. It could be improved by mentioning the return format or clarifying the investigation process, but it does not leave critical gaps.

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 both parameters (topic, objective) are already documented. The description adds context about the output format but does not add significant meaning beyond the schema itself, which already states 'Topic to investigate' and 'Decision-oriented investigation objective'.

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 investigates a topic and produces machine-readable web intelligence with specific output components (facts, evidence, confidence, agreements, conflicts, source URLs). This distinguishes it from generic search tools, though it does not explicitly differentiate from sibling tools like research_answer or search_evidence.

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 use this tool versus its siblings. It does not mention when an agent should prefer this over search_evidence, research_answer, or other search-related tools, nor does it offer any exclusion criteria.

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