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

No annotations are provided, so the description carries the full behavioral burden. It discloses the checks performed and that a 0-100 spoofing risk score is produced, which implies a read-only DNS audit, but it says nothing about permissions, rate limits, per-domain vs bulk cost, or failure behavior for unqueryable domains.

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 action front-loaded and the output metric placed at the end. Every clause (the record types, the scoring range) carries information an agent needs; there is no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema and no annotations, so the description must carry the load, and it does disclose the headline return value (0-100 spoofing risk). It stops short of describing the full result shape (per-record findings, pass/fail detail) or how multiple domains are handled, leaving a small gap for a one-parameter audit 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?

Only one parameter exists and schema description coverage is 100%, so the schema already fully documents 'domains'. The description adds no syntax, batching, or format guidance beyond what the schema states, making the baseline 3 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?

States a specific verb (audit) plus the exact resource and enumerates every record family inspected (SPF, DMARC, DKIM, BIMI, MTA-STS, TLS-RPT, MX) and the deliverable (spoofing risk score 0-100). This is clearly distinguishable from sibling tools like score_email_deliverability_risk or monitor_ssl_tls_certificates, which cover different surfaces.

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 enumerated check list implies when the tool is relevant (you want a domain's email authentication/spoofing posture), but there is no explicit when-to-use, when-not-to-use, or named alternative versus score_email_deliverability_risk. Usage is inferable rather than 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 carries the full behavioral burden. It discloses the analytical gates performed, including 1,000-run Monte Carlo stress and MQL5 linting, which gives useful insight into the tool's internal behavior. It does not state whether the operation is read-only, what permissions are needed, runtime expectations, or what the response contains, leaving significant 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?

The description is a single front-loaded sentence that states the purpose first and then enumerates the gates. Every element contributes to understanding the tool, and there is no filler. It is dense but appropriately sized for the complexity of the operation.

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?

This is a complex analytical tool with seven gates, no output schema, no annotations, and incomplete parameter documentation. The description gives a useful high-level overview but omits return values, output structure, parameter meanings, and any performance or side-effect context. An agent would need substantially more information to invoke it with confidence.

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%: the strategies parameter is documented, but initialBalance and monteCarloRuns have no descriptions. The tool description never explains what any parameter means, what the strategies object should contain beyond the schema's brief hint, or how initialBalance and monteCarloRuns affect the audit. It fails to compensate for the low schema 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?

States a specific verb+resource ('Audit ... backtests') and enumerates the seven institutional gates, making the tool's function immediately clear. It is easily distinguishable from the only related sibling, optimize_multi_strategy_portfolio, which optimizes rather than audits. The scope is precise enough for an agent to know what this tool does without opening the schema.

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 when the tool is useful by specifying that it audits MT5, MT4, TradingView, and quant backtests across defined gates. However, it never explicitly states when to choose this over optimize_multi_strategy_portfolio or outlines any exclusions. Usage is inferable but not directly guided.

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 behavioral burden. It does describe what the enrichment returns, but says nothing about whether the operation is a live crawl/network call, rate limits, cost, error behavior, or whether maxPagesPerSite bounds the crawl.

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 leads with the action and then lists outputs. The parenthetical example brands (Stripe, HubSpot, Salesforce, Next.js) are slightly verbose but do concretize what "tech stack signals" means.

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 annotations and no output schema, the description does a decent job covering the return payload, but leaves real gaps: no read/write profile, no rate-limit or cost note, and no explanation of the undocumented maxPagesPerSite parameter or crawling behavior.

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 50%: websiteUrls is documented, but maxPagesPerSite has no description anywhere. The phrase "domains/URLs" loosely reinforces the accepted input format, but the description does not compensate for the entirely unexplained crawl-depth 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 states a specific verb ("Enrich") and resource ("company domains/URLs") and enumerates the concrete outputs (tech stack signals, role emails, social links), so an agent knows exactly what it produces. It stops short of naming how it differs from overlapping siblings like find_and_verify_corporate_emails, which also touches emails.

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 guidance, no prerequisites, and no mention of when a sibling tool (e.g., email finding or domain security auditing) would be the better pick. Usage is only implied by the output list.

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 behavioral burden. It discloses the MX fingerprinting mechanism (Google Workspace, Microsoft 365, Proofpoint, Mimecast), which is valuable context, but says nothing about error handling, rate limits, verification depth, or side effects.

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. It is dense but efficiently readable, and 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?

With no output schema and no annotations, the description leaves what the tool actually returns unspecified (email addresses? verification status? confidence?). For a tool that resolves and verifies data, the lack of return-value context is a notable gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all three parameters are fully documented in the schema itself. The description only broadly maps to those inputs ('prospect names and company domains') and adds no syntax or format details beyond what the schema already 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?

States a specific verb and resource: 'Resolve and verify B2B corporate email addresses.' The added detail of MX provider fingerprinting distinguishes it from generic enrichment tools, though it doesn't explicitly name a sibling alternative for comparison.

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 B2B prospecting scenario is implied ('from prospect names and company domains'), but there is no explicit when-to-use, when-not-to-use, or routing guidance relative to siblings like score_email_deliverability_risk or enrich_company_websites.

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

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

With no annotations, the description carries the full burden. It does disclose the data source ('authoritative IANA RDAP'), which implies a live registry lookup and a read-only operation, and it enumerates returned fields. It says nothing about failure modes for unregistered/invalid domains, rate limits, or latency, which for a network-dependent lookup tool is a meaningful omission.

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 most important capability (registration/expiry inspection) front-loaded. The long field enumeration is slightly list-heavy but every item earns its place by telling the agent what data comes back.

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 usefully enumerates the returned fields, which substitutes for a return-value spec. Missing only edge-case behavior (invalid domains, RDAP unavailability, rate limits) for what is otherwise a simple one-parameter read 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?

Only one parameter exists and schema description coverage is 100%, so the schema already fully documents 'domains'. The description adds no batching semantics, expected format, or limit on list size, so the baseline 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 ('Inspect') and a precisely scoped resource (domain registration data) and enumerates the exact fields retrieved: age, expiration, registrar, nameservers, DNSSEC, EPP transfer-lock. This clearly separates it from siblings like monitor_ssl_tls_certificates and audit_domain_email_security, though it never explicitly names those alternatives.

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 or when-not-to-use guidance, and no alternatives are named. The tool's applicability (checking expiry/registration status) is only inferable from the name and the field list, not stated as guidance.

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 usefully reveals that it performs live handshakes (outbound network activity, latency) and tracks fingerprint drift (implies state/comparison across runs), but says nothing about rate limits, auth requirements, whether anything is modified, or how drift is determined.

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 action and enumerates the exact inspection targets. Every clause maps to a real capability, though the enumeration is list-like rather than explaining what the agent gets back.

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 no output schema and no annotations, the description covers what is inspected but not how results are returned, what 'fingerprint drift' means operationally, or any safety/networking constraints. Adequate but leaves real gaps an agent must guess at.

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% for the single 'domains' parameter, so the schema already explains it is a list of hostnames/domains. The description's 'across hosts' adds only a marginal hint about bulk input and no format or syntax detail 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?

States a specific verb (Inspect) and resource (live TLS handshakes, certificates, SANs, fingerprints) with enough detail to distinguish it from generic domain tools. However, it never differentiates itself from the nearest sibling, monitor_domain_rdap_expiry, which also monitors domain-related expiry, leaving the agent to infer the boundary.

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?

'Across hosts' and 'live' imply a bulk external-scanning use case, so usage context is implied rather than stated. There is no explicit when-to-use, no exclusion of cases better served by audit_domain_email_security or monitor_domain_rdap_expiry, and no prerequisites such as network reachability.

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

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

With no annotations provided, the description carries the full disclosure burden. It does reveal the substantive computational behavior (collinearity detection, Live/Reserve tiering, risk-parity and half-Kelly sizing bounded by a drawdown budget), but says nothing about side effects, determinism, permission needs, or what the caller receives back.

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, listing the pipeline stages in order. It is dense with domain jargon (Tier-1 Live, Tier-2 Reserve, Half-Kelly) but every clause maps to an actual capability rather than padding.

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 4-parameter analytical tool with no annotations, no output schema, and low schema coverage, the description is not complete enough. It never states the return shape (rosters, weights, sizing output) or how the required strategies payload is consumed, leaving real gaps 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 coverage is only 25%, so the description must compensate and mostly does not. 'Max Drawdown budget' loosely maps to targetMaxDrawdownPct, but initialBalance, maxPairwiseCorrelation, and the required strategies object structure are left entirely to the schema, which only documents strategies.

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 ('Construct ... portfolios') and resource (multi-strategy portfolios) with concrete mechanics: collinearity detection, tier rosters, risk-parity/half-Kelly sizing. The domain is distinctive enough from the email/domain siblings, but it does not distinguish itself from the one adjacent sibling, audit_trading_strategy_overfitting.

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 or when-not-to-use guidance, no prerequisites, and no reference to the sibling that operates on trading strategies. The agent must infer from the name alone that this is the portfolio-construction tool rather than the strategy-audit tool.

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, and it does disclose the scoring range and the three-way output classification. It says nothing about determinism, rate limits, cost, or whether the classification is per-address or aggregate, leaving meaningful behavioral gaps for a mutation-free but non-trivial analysis 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?

One sentence that front-loads the core action (score B2B email lists), then the output semantics (0-100, risk type) and the action mapping (send/review/suppress). No filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description usefully explains what comes back: a 0-100 risk score and a per-address send/review/suppress label. That is adequate for a one-parameter tool, though it omits how the score is delivered (structure, aggregation) and any limits on list size.

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% for the single 'emails' array parameter, whose description already states it is the list of addresses to score. The tool description adds no format, size-limit, or batching guidance beyond the schema, so the baseline 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 (score) and resource (B2B email lists) plus the scale (0-100) and the resulting classification (send/review/suppress). This clearly separates it from sibling tools like find_and_verify_corporate_emails (find) and audit_domain_email_security (audit), though it never names an alternative 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?

The phrase 'before outbound campaigns' implies the usage context, so an agent can infer when the tool is relevant. However, there is no statement of when NOT to use it, no prerequisites, and no routing to a sibling tool if the agent needs discovery/verification instead of scoring.

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