AstraVerify Domain Trust Check

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

Annotations already declare this tool read-only, idempotent, open-world, and non-destructive, so the description does not need to re-state safety. It adds useful behavioral context beyond annotations: the result is a score and each finding is tied to an exact file or tag to fix. It does not mention any network-side crawl activity or rate-limit behavior, but the schema's refresh parameter already communicates the cached/fresh logic.

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 tight sentence fully front-loads the tool's purpose and uses a colon-separated list to enumerate the assessment areas plus the actionable output. There is no filler, no repetition of the title, and no unnecessary restating of schema 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?

The tool has no output schema, so the description carries the responsibility of explaining return value intent; it does so by naming the score and the per-finding file/tag fix. It omits the score's scale or output format, but for an agent selecting and invoking the tool with one required domain parameter and an optional refresh flag, the description is sufficiently 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 100%, with domain documented as the raw user-provided domain (no scheme/path, reserved names refused) and refresh documented as forcing a fresh scan with rate limiting. The description adds no parameter-level detail beyond the generic reference to 'domain'. At full schema coverage, the 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 identifies the tool as producing a discoverability score for a domain and enumerates concrete dimensions: crawl access, site plumbing, page metadata, structured data, and answer-engine readiness. It also promises actionable output, the exact file or tag to fix each finding. It falls just short of a 5 because it is phrased as a noun phrase rather than a direct verb and does not explicitly distinguish itself from the sibling fetch_as_crawler.

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 use case: evaluate and improve a domain's search/AI discoverability, and get concrete fixes. However, it never names alternative sibling tools or states when not to use this tool versus fetch_as_crawler, check_email_security, or verify_fix. Usage guidance is present only by inference from the tool name and topic, not by explicit routing.

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, idempotentHint, and destructiveHint=false, covering safety. The description adds output composition (score, found records, fix records) but does not disclose behavioral details such as caching/rate limits, which are only in the refresh parameter schema.

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 efficient sentence that front-loads the core purpose (score for a domain) and packs output details into one trailing clause. There is no filler or repetition of schema 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 simple 2-parameter tool with rich annotations, the description is mostly complete: it names the return payload (score, DNS records found, exact records to publish) and the schema handles parameter details. It does not mention the sibling verification workflow or caching expectations, so a bit of context is left out.

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 domain and refresh are already documented, including domain format and reserved-name refusal as well as refresh's caching/rate-limit behavior. The description only adds 'DNS records found' and fix records, which relate to output rather than 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 states the tool produces an email security score for a domain plus the DNS records found and exact remediation records, with the title naming MX/SPF/DKIM/DMARC. This is a specific resource+outcome that is easily told apart from check_discoverability, fetch_as_crawler, and verify_fix.

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 tool's email-security/DNS focus implies using it when a domain's email authentication or fix records are wanted. However, it does not explicitly mention when to prefer it over siblings like check_discoverability or verify_fix, so routing relies on inference from the name/title.

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 cover read-only, idempotent, and non-destructive traits. The description adds behavioral value by disclosing the output contents and the CDN/firewall insight, which is not deducible from annotations alone. No contradictions.

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 filler. The first sentence front-loads the purpose and the second delivers the unique selling point. Every word earns its place, and the structure is immediately scannable.

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 (2 params, no output schema). The description covers what it returns and its unique behavioral advantage. An agent can confidently select and invoke it without further clarification.

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 50% (domain has a description; agent only has an enum). The tool description lists the agent values redundantly with the enum and mentions 'as a named crawler', but adds no new syntax or constraints beyond what the schema already states. For a two-parameter tool with self-explanatory enum, this is adequate but not enriched.

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 (fetch) and resource (root page as a named crawler), and enumerates the exact output (status, redirects, headers, extracted text). It clearly distinguishes from siblings by emphasizing it shows CDN/firewall blocks that robots.txt cannot, which implies a unique value proposition.

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?

Provides clear context on what the tool reveals (what a specific bot receives, including blocks beyond robots.txt). It does not explicitly name alternatives or exclusions, but the description makes the use case self-evident against siblings like check_discoverability.

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 declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety and side-effect behavior. The description adds value by specifying the report's output structure (scores, fixes, link), but it does not disclose any additional behavioral traits such as caching, rate limits (though the schema covers refresh), or error conditions. With annotations providing the baseline safety profile, the description's contribution is moderate, so a 3 is appropriate.

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 key outputs and includes a usage directive. There is no redundancy, and every clause contributes to the agent's understanding of what to expect and when to call it. It is appropriately concise and well-structured.

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 read-only report tool with two well-documented parameters and no output schema, the description provides enough information: it lists the three main result types and gives a clear usage context. It does not elaborate on response format or potential failure modes, but given the low complexity and the annotations covering safety, this is not a significant gap. The tool is adequately specified for an agent to invoke 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 100%; both parameters (domain and refresh) have detailed descriptions, including constraints and rate-limit notes. The tool description itself adds no parameter-specific information beyond what the schema already provides. Per the rubric, a baseline of 3 applies when schema coverage is high and the description doesn't need to compensate.

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 lists the report's contents ('Both scores, the open fixes ranked by severity, and the shareable report link') and ties it to a common question, making the tool's purpose clear. It does not explicitly state the verb 'returns' or 'gets,' but the tool name and context supply that. It also distinguishes itself from siblings by indicating it is the first step for overall setup questions.

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 this tool: 'Use this first for "is my domain set up right?" questions.' This provides a clear trigger condition. It does not explicitly mention alternatives or exclusions, but the implication that this is the entry point for general checks versus specific checks (e.g., check_discoverability) is strong enough for an agent to route correctly.

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 declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so safety behavior is covered. The description adds scoping and return-value context, but does not disclose additional behavioral traits like caching, failure modes, or prerequisites. That matches a middle 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?

A single sentence delivers the action, scope, accepted values, and result without filler. The information is front-loaded and every word 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 simple, read-only tool with two required parameters, the essential invocation details are covered: domain format comes from the schema, component choices are listed, and the return behavior is stated as an 'updated score'. It would be more complete with a brief explanation of what each component represents and the score's format or range.

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 domain parameter is well-described in the schema, but component has only an enum with no field-level explanation. The description clarifies that component selects 'checks behind one component' and repeats the enum values, partially compensating for the 50% schema description coverage. It does not define what each component means or add domain-level details.

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 precise action ('Re-runs only the checks'), a specific resource ('one component'), enumerates the accepted components, and names the output ('returns the updated score'). The word 'only' differentiates it from a full discoverability check, making it easy to pick apart from sibling tools like check_discoverability.

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 title 'after a fix' and the verb 're-runs' clearly convey the intended use case: targeted re-verification after a fix. However, the description does not explicitly name an alternative for full audits or state when not to use this tool, 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.