LastDatabase – B2B & B2C Lead Data MCP

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

Annotations already declare readOnlyHint=true, destructiveHint=false and a closed world, so safety is covered. The description adds genuinely non-obvious business behavior: it takes no arguments and, importantly, 'does not consume lead records' — a cost/side-effect detail the annotations cannot express.

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?

Three short sentences, front-loaded with the core purpose, then scope/no-args, then usage guidance. Every sentence carries distinct information with no repetition.

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 zero-parameter status read with no output schema, the description covers purpose, usage timing and the key side-effect caveat. It stops short of describing the return shape (e.g. a numeric balance), which is the one remaining gap for a tool with 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?

There are zero parameters, so the baseline is 4. The description reinforces this by stating it 'accepts no arguments,' which matches the empty schema with additionalProperties=false, though there is nothing further to clarify.

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 (Retrieve) and resource (the authenticated customer's subscription record allowance), a purpose no sibling tool shares — the siblings are all search/unlock/verify operations. An agent can immediately tell this is an account-status read, not a lead lookup.

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 clear when-to-use context: 'Use before requesting protected lead access or when the customer asks about remaining usage.' This ties it to the protected-lead workflow (e.g. unlock_people), though it never names an alternative tool or an explicit when-not-to-use condition.

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 establish the safe read-only profile (readOnlyHint=true, destructiveHint=false). The description adds non-obvious behavior the annotations cannot convey: searches do not consume lead allowances, and returned emails are masked with plaintext access governed by existing permissions.

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?

Four sentences, front-loaded with what the tool does, then the routing rule, then non-obvious behavior. Every sentence carries information; the pagination sentence slightly overlaps the schema's documented limit/offset but still sets an overall cap.

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 discloses the return shape (masked emails) and the permission gating on plaintext, plus pagination behavior. It is complete enough for correct invocation, though it does not describe ordering or result-count semantics for pagination.

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 six parameters (city, state, country, keyword, limit, offset) are already documented in the schema. The description only restates the filter dimensions and the limit/offset pagination with a 50-record cap, adding no syntax or format detail beyond the schema. 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 (Search) plus resource (LastDatabase consumer email records) and enumerates the filter dimensions. It explicitly distinguishes itself from the professional/B2B contact tools, so an agent can route between search_consumer_emails and search_people/search_hot_leads without inspecting schemas.

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 a clear selection rule: 'Use this tool for consumer email discovery rather than B2B professional contacts.' That is explicit when-to-use/when-not guidance, though it does not name the actual sibling tool(s) to use instead for B2B.

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 the safe read-only, non-destructive, non-open-world profile, and the description adds real value beyond them: search does not consume lead allowances, and email/phone are masked in results. It still omits return-field detail, but the allowance and masking disclosures are meaningful behavioral context.

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?

Purpose is front-loaded in the first sentence and every subsequent sentence carries distinct information (dataset routing, interpretation caveat, allowance cost, masking, pagination). 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?

For a zero-required-parameter search with no output schema and fully documented params, the description covers routing, cost, and result masking. It is close to complete, though it does not describe the returned record 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 description coverage is 100%, so every parameter (page, per_page, gender, country, keyword, category, industry) is already documented. The description restates the filterable fields and notes the 50-per-page cap but adds no format or syntax detail 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 (Search) and resource (LastDatabase Hot Lead dataset) and enumerates the filterable facets. Naming the dataset explicitly helps route it among the sibling search_* tools, though it never directly contrasts itself with the closest alternative, search_mixed_leads.

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?

'Use when the customer specifically requests records from the Hot Lead dataset' gives a clear selection condition tied to the dataset name. No when-not guidance or named alternative tool is provided, so it stops short of full routing 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?

Annotations already declare readOnlyHint/destructiveHint, so the safety profile is covered. The description adds substantive behavior beyond that: search does not consume lead allowances, email/phone fields stay masked, plaintext access follows customer permissions, and per_page caps at 50. It does not describe result ranking or ordering, but the added operational context is rich.

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 primary action and filters, then usage guidance, then behavioral caveats in tight sentences. Every sentence carries either routing, safety, or limit information with 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, but the description covers the information an agent needs: filter scope, when to choose this over siblings, the no-allowance and masking behavior, permission gating, and pagination limits. Nothing essential is missing 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 all seven parameters are already documented in the schema (including page/per_page defaults and bounds). The description restates the filter dimensions and pagination but adds no syntax, matching behavior, or format detail beyond the schema. Baseline 3 is correct when the schema does the heavy lifting.

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 (LastDatabase mixed lead records) with the exact filter dimensions it accepts. It explicitly distinguishes itself from the dedicated B2B contact, consumer email, and phone datasets, which are distinct siblings (search_people, search_consumer_emails, search_phone_leads).

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 gives an explicit when-to-use: 'Use when the customer requests mixed lead data rather than a dedicated B2B contact, consumer email, or phone dataset.' This names the alternatives and the condition that selects this tool over them, leaving little 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 cover the safe-read profile (readOnlyHint, destructiveHint=false), and the description adds genuinely non-derivable behavior: searching does not consume lead allowances, protected emails stay masked unless owned. The 'up to 50 per request' line partially restates the schema's limit maximum.

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?

Short, front-loaded sentences with the core capability first, then routing, cost behavior, and result cap. Slightly redundant in repeating the 50-result bound already enforced by the schema maximum.

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 does the work of explaining returns: up to 50 contacts, masked email caveat, and the unlock path. It still omits what fields a returned contact contains, which is the main remaining gap for an agent composing follow-up calls.

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 nine filter parameters are already documented in the schema. The description only restates the filter dimensions (city, state, industry, etc.) without adding format, matching semantics, or combining behavior for any parameter. 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 (Search) plus resource (B2B business contacts) and enumerates the filtering dimensions, and clarifies it returns individual professionals/decision-makers rather than companies. It implicitly separates itself from siblings like search_consumer_emails, but never names a sibling to route the agent 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?

Gives clear context for use ('discover individual professionals and decision-makers') and routes a follow-up action to unlock_people for accessing a selected contact. It lacks explicit when-not-to-use guidance or a stated alternative for other search tools in the sibling set.

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 the safety profile (readOnly, non-destructive, closed-world). The description adds two genuinely useful behavioral facts beyond them: search does not consume lead allowances (cost behavior) and phone numbers stay masked until the authorized workflow is used (data-access 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?

Front-loaded with purpose, then usage trigger, cost note, masking note, and pagination. Four sentences that mostly earn their place, though the enumerated filter list partially duplicates 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?

Given full annotation coverage, no output schema, and 100% schema coverage, the description is complete enough: it conveys purpose, cost, masking, and pagination. It could still note result ordering or the absence of a required filter, but nothing critical 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 description coverage is 100%, so each filter parameter is already documented. The description echoes the filter list and adds pagination context (limit/offset, up to 50 records) but no syntax or format detail beyond the schema, 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 (Search) and resource (LastDatabase phone lead records) plus the dimensions searched. It implicitly distinguishes itself from siblings like search_consumer_emails and search_hot_leads by naming the 'phone lead' resource, but never explicitly contrasts 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?

"Use when the customer requests phone-number lead discovery" gives a clear usage trigger. However, it offers no exclusions or guidance on when to prefer sibling searches such as search_hot_leads, search_mixed_leads, or search_people.

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 only declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false); the description goes far beyond by disclosing credit-consumption semantics (invalid/risky/catch-all/disposable/unknown results consume zero records, previously owned contacts do not re-charge) and the suppression + real-time verification pipeline. It also states the customer-notification obligation, which no annotation conveys.

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 action and selection criteria are front-loaded, and the billing/verification edge cases that follow each carry real decision value. It runs long for a one-parameter tool, with some sentences (e.g. the zero-record enumeration) that could be tightened, keeping it just short of ideal.

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 only safety annotations, the description does the heavy lifting on billing, verification outcome handling, and the pre-invocation customer notice. It does not say what an unlocked record actually returns (email, phone, or both), which is the one remaining gap for an agent deciding what to do with the result.

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 lead_id parameter already documents itself as coming from search_people, so the schema carries the load. The description repeats the provenance but adds no format, range, or validity nuance beyond it, which is the expected baseline when the schema is complete.

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 (unlock), a precise resource (one B2B contact), and the identifier that selects it (lead_id from search_people). An agent can immediately distinguish this from the sibling search_* and verify_email tools, which enumerate or validate rather than unlock.

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 a clear triggering condition ('only when the customer requests access to a specific contact') and a prerequisite step (the contact must first be identified via search_people). It stops short of naming alternatives, e.g. that search_people is what surfaces lead_ids or that verify_email handles standalone validation, so the routing is implied rather than exhaustive.

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 adds real behavioral value with the interpretation caveat that results 'must not be presented as a guarantee of future deliverability'. However, with readOnlyHint=false the annotation implies this operation may not be a pure read (likely credit-consuming), and the description never mentions credit cost or side effects, leaving a notable gap.

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?

Four sentences, front-loaded with purpose followed by the input requirement and usage rule. Reasonably tight, though the caveat sentence is somewhat boilerplate and could be trimmed.

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 covers purpose, input requirement, usage condition, and how to interpret results. It is nearly complete, missing only the possible credit/side-effect disclosure implied by readOnlyHint=false.

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?

There is only one parameter and schema coverage is 100%, so the schema already documents 'email' with format:email and an example. The description reinforces the syntactic-validity requirement but adds no format or syntax detail beyond the schema, fitting the baseline of 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?

The description states a specific verb (verify) and resource (a single business email address) and adds the engine name, making the scope unambiguous. It implicitly differentiates from the discovery-oriented siblings (search_*, unlock_people) by framing this as validation rather than contact discovery.

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 gives a clear triggering condition: 'Use this tool when a customer requests email validation rather than contact discovery.' This contrasts usage against the discovery siblings, though it does not name a specific sibling tool or state explicit exclusions.

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