LeadBoxer: company and contact enrichment, IP to company

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered. The description's 'Does not use credits' largely restates destructiveHint=false, and it adds only light value by naming what is returned (grants and expiry dates). No error or empty-balance 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?

Two short sentences, front-loaded with the purpose, followed by the extra behavioral note. Nothing is redundant or padded.

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 parameters, no output schema, and rich annotations, the description covers the essentials and hints at the return contents. It stops short of specifying the response shape (e.g. numeric balance vs. structured grant list), which matters slightly since there is no 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 tool takes zero parameters, so there is nothing for the description to disambiguate. Baseline 4 applies; the description correctly signals the tool is account-scoped and takes no input.

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 ('Show how many LeadBoxer credits this account has left') and adds the returned detail (active credit grants and expiry dates). It is clearly distinguishable from the lookup_* siblings, which are external-data lookups rather than account status reads.

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 clearly implied by the description: call this to inspect the account's remaining credit balance. The clause 'Does not use credits' preempts a common worry about invoking a balance check. There is no explicit when-not guidance, but the siblings are unrelated so no routing decision is needed.

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 readOnly, idempotent, openWorld and non-destructive, so the ethical bar is lower. The description adds a genuinely useful non-schema fact: 'Uses LeadBoxer credits per call', which warns the agent this is a metered operation. It does not cover failure modes (unknown domain, insufficient credits), keeping it at 4.

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 paragraph: what it returns first, then use cases, then the credit cost last. Dense but every clause carries information. The parenthetical '(company lookup, firmographics)' is mildly redundant with the title.

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 enrichment tool with no output schema, the description supplies the field list (so the return shape is known), the input format, usage contexts, and the credit cost. Only error/quota behavior is unaddressed.

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 single 'domain' parameter is documented with examples and format constraints in the schema itself. The description's 'stripe.com (no https:// or www)' merely repeats the schema's example and guidance, adding no new semantics — baseline 3.

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 ('Company enrichment by domain') and enumerates the returned fields (name, industry, employee range, HQ, phone, LinkedIn, specialties, aliases). Sibling tools lookup_email, lookup_ip and get_credit_balance are clearly different resources, so the agent can route without opening a 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?

Gives concrete use cases: enriching sign-ups and CRM accounts, scoring ICP fit, and profiling a company from a work email's domain — the last implicitly routes between this and lookup_email. There is no explicit 'do not use when' or cost-alternative guidance, so it stops short of a 5.

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

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

Annotations already flag readOnly/idempotent/openWorld, but the description adds the facts that actually change agent behavior: a cost of 50 LeadBoxer credits per profile found, and that nothing is charged on a miss. It also discloses that optional hints improve match rates, which is not recoverable from annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose and returns, then constraints and cost, with zero filler sentences. The parenthetical 'reverse email lookup, contact enrichment' mildly duplicates the opening phrase, keeping it just short of 5.

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 no-output-schema tool, the description enumerates the returned profile fields (name, headline, LinkedIn URL, seniority, function, location, languages, work history), so the agent knows what it gets back. Cost, hit/miss billing, and exclusion scope are all present; nothing material is missing.

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 already labels every parameter as optional hints 'to improve matching', so the description's 'Optional name and company hints improve matching' largely restates it. Baseline 3 is appropriate; the description adds consolidation but no new parameter semantics.

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+resource ('Email to person… reverse email lookup'), enumerates the returned fields, and explicitly separates itself from lookup_domain ('For the company's firmographics, call lookup_domain'). It also states a negative scope boundary ('Does not find or verify emails'), so an agent can place the tool precisely among its 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?

Concrete usage contexts are given ('enrich new sign-ups, leads and CRM contacts'), the alternative for company data is named with the exact routing condition, and the exclusions are stated. Nothing about when to call this versus lookup_domain is left 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?

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely useful context beyond that: the enumerated return fields, IPv4/IPv6 support, and crucially that each call consumes LeadBoxer credits — a cost signal annotations cannot convey.

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?

Front-loaded with the core mapping, then return fields, then usage, chaining and cost — every sentence carries information. The parenthetical 'reverse IP lookup, B2B website visitor identification' is slightly redundant marketing framing but takes little space.

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 compensates by enumerating the returned fields (name, domain, ISP, connection type, location components). Cost, chaining, and input types are all covered, leaving nothing an agent needs to call it 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 coverage is 100% and the single 'ip' parameter is fully documented (IPv4/IPv6 examples in the schema). The description's mention of IPv4/IPv6 largely restates the schema, so 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+resource (IP → company identity) and immediately clarifies the reverse-lookup/B2B use case. The title and description together make it unmistakable versus lookup_domain and lookup_email.

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?

Gives concrete usage contexts (web logs, analytics, sign-ups, security alerts) and routing guidance ('Chain with lookup_domain for full firmographics'). It does not explicitly say when to skip this tool in favor of lookup_domain alone, so it falls short of a full when/when-not statement.

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