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

No annotations are supplied, so the description carries the full burden: it does not say whether the tool performs live network fetches against the target domain, whether it is read-only, what rate limits or auth requirements exist (the proApiKey parameter hints at a quota model but this is unstated), or how partial failures are reported. It only names the checks performed.

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 dense sentence with the verb and scope front-loaded and the three audit dimensions enumerated. No filler, no restatement 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?

For a five-parameter tool with no annotations and no output schema, the description is minimal but workable: it conveys scope but not return shape, scoring criteria, or the difference between live lookups and offline mode. An agent could select the tool correctly but would be guessing about results and cost.

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 domain, html, llmsTxt, robotsTxt, and proApiKey. The description mentions the artifact types (robots.txt, llms.txt) but adds no meaning beyond the schema and does not explain the offline-testing mode that three optional parameters enable.

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 ('Audit') plus resource ('any domain') and enumerates the three concrete checks: /llms.txt support, robots.txt AI-bot rules naming GPTBot/ClaudeBot/PerplexityBot, and Schema.org metadata. This clearly separates it from siblings like audit_domain_wcag_and_eaa and scan_domain_cyber_hygiene, though it never names those siblings explicitly.

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 statement of when to choose this tool over alternatives, no prerequisites, and no exclusions. The agent must infer from the sibling names that this is the AI-readiness variant rather than the accessibility or security audit.

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 supplied, so the description carries the full burden, and it omits the operational facts an agent needs: that `url` triggers a server-side fetch (timeouts, unreachable targets), whether `html` is size-limited, and whether results are truncated or gated without `proApiKey`. The mention of 'statutory fine risk estimation' hints at a computed output but never explains its basis or reliability. It does correctly imply a read-only audit, so it is not misleading, just thin.

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 the verb, the input shape, the benchmark standards, and the differentiator (fine risk estimation) in that order. There is no filler and nothing a reader must scroll past to reach the operative 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?

With no output schema and no annotations, the description must stand in for a fair amount, and it does cover the audit target, the standards, and one headline output (fine risk). It leaves open what a report actually contains, how partial PRO results differ, and which of the two input modes to prefer, which matters for a four-parameter tool with all-optional fields.

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 all four parameters are already documented in the schema and a 3 is the baseline. The description reinforces the `standard` enum by naming both WCAG 2.2 AA and EN 301 549, and frames `url`/`html` as two input modes, but it never states that they are alternatives or what happens if both or neither are supplied. The `proApiKey` gating of 'complete violation diagnostics' is left entirely to the schema wording.

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 (Audit) and resource (website URL or HTML string) and pins the scope to named standards (WCAG 2.2 AA, EN 301 549) plus 12 criteria. That is enough to separate it from siblings like audit_domain_ai_llms_readiness or scan_domain_cyber_hygiene without opening any schema. It stops short of an explicit sibling contrast, so a 4 rather than 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?

There is no guidance on when to choose this audit over the other audit tools, nor on when to pass `url` versus `html` for the same check. With zero required parameters, the schema alone permits an empty, useless call, and the description does nothing to prevent that. Usage is only inferable from the tool name and topic.

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 implies a read-only detection operation and lists what is detected, but it does not state authentication requirements, rate limits, whether a URL, HTML, or domain input is preferred, or what kind of response is returned.

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 with no filler. Every phrase contributes to the detection scope.

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 description covers the detection categories, which gives an idea of the output. However, with no output schema and no annotations, it does not explain return structure or how to choose between url, html, and domain inputs, leaving meaningful gaps for a four-parameter enrichment 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 description coverage is 100%, so the schema already explains the four parameters. The description adds no parameter-level meaning beyond that baseline, so a 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 states a specific verb, 'Detect', and a specific resource/scope: e-commerce platform, tracking pixels, payment gateways, and EU GPSR / WCAG compliance gaps. It is clear what the tool does, though it does not explicitly distinguish itself from overlapping siblings such as audit_domain_wcag_and_eaa.

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 no guidance on when to use this tool versus alternatives, or when not to use it. Usage is only implied by the capability list, and there is no mention of the WCAG-related sibling or other nearby audit tools.

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 at all, the description carries the full behavioral burden, and it does disclose the deliverable structure (three timed emails plus a LinkedIn note) and target platforms, which is real value. However, it says nothing about cost/quota behavior implied by the optional proApiKey, whether generation is deterministic, or what form the response takes (plain text, JSON, per-email objects). For an unannotated generation tool this leaves meaningful gaps.

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 core action and enumerates the deliverable without filler. The day-by-day cadence is packed into parentheses efficiently, and nothing is redundant.

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 7-parameter, unannotated, no-output-schema generation tool, the description covers what is produced but not how to invoke it well: the relationship between triggerType, signalDetails and targetPersona is unexplained, and the output format is unstated despite no output schema existing to compensate. It is adequate to identify the tool but thin for correct invocation.

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 every parameter is already documented in the schema and a baseline of 3 applies. The description adds the conceptual link between the tool and the seven triggerType enum values only indirectly; it never explains how signalDetails or targetPersona shape the personalization. It adds little meaning beyond the structured fields.

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 gives a specific verb (generate) and a concrete artifact: a 3-step cold email sequence with named cadence (Day 1 Hook, Day 4 Value, Day 8 Break-Up) plus a LinkedIn connection note, targeted at Instantly.ai / Smartlead. This is clearly distinct from the sibling tools, which all scan or audit domains for signals. It stops short of a 5 because it never explicitly contrasts itself with those trigger-scanning siblings.

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 explicit when-to-use statement, no prerequisites, and no mention that triggerType should be derived from the output of the sibling scan tools (gov/sec triggers, WCAG audit, cyber hygiene, etc.). The only contextual hint is the trailing 'for Instantly.ai / Smartlead', which identifies the destination platform but not the selection criteria. Usage is implied at best.

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 supplied, so the description carries the full behavioral burden, yet it only implies read-only via 'live statistics'. It says nothing about whether the aggregation is expensive or slow across all datasets, whether a missing or invalid proApiKey degrades results silently, caching freshness, or what tier of statistics arrives without the key. That last point matters most since it changes the result the agent receives.

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 no filler or repetition. It is well sized for what it conveys, though the brevity edges toward under-specification rather than polished concision.

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, the description is the only place an agent could learn what the aggregate actually contains, and it stops at 'live statistics'. For a two-parameter aggregating tool whose entire value is the shape of the returned summary, that leaves the caller unable to predict the response.

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% and both optional parameters are documented there, including the default for 'detailed' and that proApiKey unlocks extended metrics. The description adds no meaning beyond that, so the baseline 3 for fully-documented schemas applies.

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-and-resource pair: 'Aggregate live statistics' over 'all active B2B lead datasets and products in the Prong 2 Marketplace Suite'. The scope is clear enough to distinguish it from the domain-scanning and sequence-generation siblings, which all operate on a single domain or campaign. The only weakness is unexplained jargon ('Prong 2 Marketplace Suite') that an agent cannot resolve from the description alone.

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 when-to-use guidance, no exclusions, and no named alternatives. The description never says whether this is the right first call to orient in the suite, or a reporting call to run after the individual audits, leaving the agent to infer its role from the word 'Aggregate'.

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 supplied, so the description carries the full burden. It does disclose the data sources and the categories of extracted signal, which is genuinely useful. However, it omits read-vs-write framing, rate limits and the free-tier cap (visible only in the schema), what a 'signal' record actually contains, and whether a Pro key changes 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?

A single dense sentence with the resource front-loaded and no filler. Every clause names a distinct output category, so nothing could be trimmed without losing 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 six-parameter, all-optional scanning tool with no annotations and no output schema, the description leaves key gaps: it never defines what a returned signal looks like, whether results are across boards or per-company, or how the free-tier cap and Pro key affect results. It is minimally adequate but not complete for the complexity.

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 all six parameters are already documented in the input schema; baseline is 3. The description adds only loose context by tying the tool to Greenhouse/Lever boards, which maps to the atsProvider and board params but gives no guidance on how company, roleKeyword, and maxResults interact or what happens with zero required params.

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 (Query) plus concrete resources (Greenhouse and Lever ATS boards) and names the three outputs it extracts: migration pain signals, disclosed USD salary budgets, and vendor opportunities. This is far more specific than the sibling tools, which target domains, SEC filings, and storefronts, so an agent can route correctly without opening the schema. It stops short of explicitly contrasting itself with any sibling, which keeps it at 4.

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 'immediate B2B vendor opportunities' implies a sales/prospecting use case, but the description never states when to call this versus a sibling or what preconditions exist (e.g. whether a company or board must be known first). Usage is inferable rather than prescribed.

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 supplied, so the description carries the full disclosure burden. It does convey the checks performed and that results are scored for spoofing vulnerability with sales-oriented framing, and "Scan" conventionally implies a non-destructive read, but it never states return shape, whether the domain must resolve, or what the free tier limits are versus the pro key.

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 dense sentence that front-loads the scanned artifacts and closes with the two value outputs. Every clause adds information and nothing is repeated from the 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?

For a two-parameter read-only scan with no output schema, the description covers what is inspected and what is returned in concept (vulnerability scores and sales angles). The main residual gap is operational behavior, such as rate limits or failure modes, which matters more given the absence of annotations.

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 both parameters are already documented, including the proApiKey as the unlimited-audit credential. The description adds no meaning beyond the schema, so the baseline of 3 applies.

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 "Scan" with an enumerated resource set (DNS SPF, DMARC, MX records, plus HTTP security headers HSTS/CSP/XFO) and states the outputs (spoofing vulnerability scoring and MSSP sales angles). This distinguishes it clearly from the sibling domain audits, which cover WCAG/EAA and AI-LLM readiness rather than email/DNS security posture.

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?

Usage is only implied: the framing of spoofing risk plus "MSSP sales angles" suggests it fits security-gap prospecting. There is no explicit statement of when to call it versus the sibling audit tools, nor any exclusion such as domains without mail records.

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. 'Search' and 'live' imply a read-only, real-time query, and it usefully discloses the output shape (0-100 deterministic score plus outreach briefs). However, it says nothing about rate limits, pagination, per-source auth requirements, or the free-vs-PRO behavior that the proApiKey and maxResults params imply.

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 packs sources, scoring, and output type with no filler. It is dense but every clause earns its place; only minor loss for cramming three ideas into one sentence without structural separation.

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 seven parameters, no annotations, and no output schema, the description does cover the essentials: what is searched, where the data comes from, and what comes back. It omits the tiered-access model (free cap of 5 results vs PRO enrichment) and any latency or reliability expectations, leaving meaningful gaps for a tool this complex.

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 every parameter including the source enum and defaults is already documented. The description adds no syntax, format, or interaction detail (e.g. how keywords combine with query, or how minAmount applies across sources) beyond what the schema states, so the baseline of 3 applies.

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 (Search) and concrete resources (federal contracts, grants, SEC 8-K filings), naming the underlying sources USAspending.gov and Grants.gov. It is clearly distinguishable from siblings like scan_ats_hiring_pain_signals or generate_3step_cold_sequence, though it never explicitly contrasts itself with 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?

Usage context is only implied: 'B2B buying-intent scoring' and 'cold outreach briefs' signal a sales-prospecting scenario. There is no explicit when-to-use guidance, no mention of when not to use it, and no routing to any of the seven sibling tools despite obvious overlap with ATS pain-signal scanning and sequence generation.

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