Prospect Intelligence

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

Annotations already cover readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is known. The description adds critical behavioral context beyond annotations: the per-call price ($0.10 USDC on Base via x402), the two-step MCP-plus-HTTP invocation flow, the data sources (Wikidata, Wikipedia, homepage, SEC EDGAR), the per-field provenance metadata (source, source_url, checked_at, confidence), and the null-not-guessed policy. This is exactly the kind of context 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?

The description is dense and front-loaded, leading with the resource and its fields before moving to provenance, exclusions, payment, and the invocation flow. It is on the longer side but every clause conveys distinct information; a slight trim of the source list would help but nothing is wasted.

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 the tool has an output schema, return values need not be explained, yet the description still usefully summarizes field-level provenance and null handling. The main missing piece is explicit guidance on when to choose this over enriched_lookup or prospect_brief, but for a paid public-data lookup the description is otherwise 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%, so the schema already documents both parameters with examples and the domain parameter's accuracy benefit. The description does not add parameter-level detail beyond what the schema provides, so 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 names a specific resource (public company profile) and enumerates exactly what it returns (firmographics: industry, HQ city/country, founded year, employee count, ticker, social handles). It explicitly distinguishes from siblings by stating 'Not a contact or CRM record,' separating it from email_lookup and enriched_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?

The description implies this is the base-level lookup and hints at richer siblings via 'basic' and 'Not a contact or CRM record,' but never explicitly says when to use this versus enriched_lookup or prospect_brief. It does clearly state payment requirements and the two-step flow (MCP returns payment instructions, POST /v1/basic returns the brief), which is useful guidance but not selection logic.

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 profile, yet the description adds substantial operational context: the $0.08 USDC x402 price on Base, the charge-only-on-success rule, the fact that this call returns payment instructions for a separate POST /v1/email, and the caveat that 'valid' means server acceptance, not human readership. This is exactly the behavioral detail annotations cannot carry.

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 passage that front-loads the core action before moving to output shape, pricing, and caveats. Nearly every clause earns its place, though the return-field enumeration is partly redundant with the output 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 paid, read-only lookup with an output schema present, the description covers purpose, cost model, payment flow, and verification semantics. It omits any account/credential prerequisites for the x402 payment flow, but is otherwise sufficient for an agent to invoke 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 description coverage is 100%, so the baseline is 3. The description adds the found_only semantic (public-only, no pattern inference) and explains the meaning of the returned verification statuses, but contributes little beyond the schema for first_name/last_name/full_name.

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: 'Find one person's work email at a company domain.' The phrase 'one person's' implicitly contrasts with the batch sibling find_emails_batch, but nothing distinguishes it from basic_lookup or enriched_lookup, which the agent must resolve on its own.

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 guidance on when to choose this over basic_lookup, enriched_lookup, or find_emails_batch. The found_only parameter's effect is described, and the pricing/trial condition is stated, but neither tells the agent which sibling tool fits a given request.

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 read-only/idempotent/open-world, and the description adds material behavior the annotations cannot: the x402 payment requirement ($0.75 USDC on Base), the fact that this MCP call returns payment instructions rather than the record, and that the actual data comes from POST /v1/enriched. It also commits to sourcing guarantees (every item cited, no invented names), which tells the agent how much to trust the output.

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 record contents are front-loaded and the payment mechanics come last, which matches what an agent needs first. It is a single dense run-on sentence, but nearly every clause carries distinct information (contents, optionality, price, routing, read-only) rather than 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?

An output schema exists so return values need no explanation, and the description still covers the non-obvious parts: cost, the two-step payment-then-HTTP flow, optional icp input, and citation guarantees. Nothing an agent needs to call this correctly or interpret the response appears to be 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 the nested icp object, domain, and company are already documented with examples and semantics. The description only restates that icp is optional and that domain improves accuracy, adding little beyond the schema. Baseline 3 is appropriate when the schema carries the load.

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 resource (enriched prospecting record) and enumerates its contents: buying signals, job-board roles, ICP fit score, cited sales brief, next actions. It explicitly positions itself relative to the sibling basic_lookup ('everything in basic_lookup plus...'), so an agent can distinguish them without opening either 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 'everything in basic_lookup plus' framing plus the explicit $0.75 price gives a clear cost/richness tradeoff for choosing this over the cheaper sibling. It does not, however, name prospect_brief or state exclusions such as when the paid route is unnecessary, so the guidance stops short of explicit when-not-to-use.

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?

Goes well beyond the readOnly/idempotent/destructive annotations: duplicates are deduped to one lookup, a single contact failure never fails the batch, results return in input order with summary counts, and pricing is spelled out (x402 upto on Base, $0.08 per address returned). It also discloses that this MCP call returns payment instructions for POST /v1/email/batch and that no email is ever sent.

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-loads purpose and scope in the first clause, then layers output equivalence, failure semantics, pricing, and safety. It is a single dense paragraph that is slightly overloaded with payment detail, but every sentence carries actionable 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?

Covers return fields, failure isolation, ordering, pricing, and safety, and an output schema exists so return-value detail is optional. The one gap is the two-step flow: it says the MCP call returns payment instructions for POST /v1/email/batch, without clarifying how the agent completes the payment and submission, leaving some ambiguity for a paid 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 domain/first_name/last_name/full_name/found_only semantics are already documented, including the 1-25 bounds and the per-contact name requirements. The description reinforces the batch size and dedup behavior but adds no format or syntax detail beyond 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?

Specific verb and resource ('Find work emails'), explicit scope ('1-25 people in one call'), and it directly distinguishes itself from the sibling email_lookup by stating results share the same fields and labels. An agent can differentiate this from email_lookup without opening either 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 clear usage context ('for cleaning a whole prospect list') and anchors equivalence to email_lookup, implying the batch is the multi-contact counterpart. It never states an explicit exclusion versus basic_lookup/enriched_lookup or when a single lookup is preferable, so it falls 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 only cover the safety profile (read-only, open-world, idempotent); the description adds the material behavior they cannot express: a per-call price, the x402 payment handshake, and the two-step pattern where this tool returns payment instructions rather than the brief itself. Those are exactly the traits that would otherwise cause a failed invocation.

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 payload is packed into essentially two sentences, with the what-is-it clause first, then pricing/payment, then 'Read-only.' Front-loading is good and there is little waste. The trailing 'Read-only.' largely duplicates readOnlyHint/destructiveHint annotations, a minor redundancy.

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?

An output schema exists, so return-value detail is unnecessary, and the description covers the remaining gaps: contents of the brief, source provenance (public sources with URLs), cost, and the mechanism for actually obtaining the brief. Nothing an agent needs to call this correctly 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 company and domain are already documented in the schema, including the 'no https' format and the crawl benefit of domain. The description adds no parameter-level meaning of its own, which is the expected baseline 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?

It names a specific resource (a sales prospect brief for one company) and enumerates exactly what it contains: overview, positioning, likely needs and talking points, from public sources with URLs. That is far more informative than the sibling lookups. It stops short of a 5 only because it never explicitly contrasts itself with basic_lookup/enriched_lookup, which the agent must infer is the cheaper alternative.

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 decisive operational context: the call costs $3.00 USDC on Base via x402, this MCP call returns payment instructions, and the actual brief is fetched via POST /v1/deep. That is the critical 'how to use' flow an agent needs. It does not state when to prefer this over the cheaper sibling lookups, so it falls short of explicit when/when-not 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?

It discloses behavior that annotations cannot convey: pricing ($0.75 USDC on Base via x402) and the critical two-step mechanic that this MCP call only returns payment instructions while POST /v1/tools actually returns the result. It also states the data-quality policy (unverified fields come back as 'unknown' rather than guessed), and its 'Read-only' claim is consistent with readOnlyHint/destructiveHint=false.

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?

It is front-loaded with the action and packs the essential payment and data-quality facts into a short block with no filler. The full re-listing of the eight enum values is redundant with the input schema and costs a 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 an output schema present, return values need not be explained, and the description covers the pricing, payment flow, and data-quality caveats an agent needs. What remains thin is routing versus the sibling lookup tools and the overlap with prospect_brief.

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 each parameter (tool, domain, person, company) is already documented in the schema with examples, so the baseline is 3. The description's only added parameter value is enumerating the valid 'tool' values, which the schema enum already provides.

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 ('Run') and resource ('one named public-source analysis') and enumerates the eight valid analyses, so the agent knows exactly what the tool does. It never contrasts itself with siblings like basic_lookup, email_lookup, or prospect_brief, which appear to overlap (e.g., generate_prospect_brief vs the prospect_brief sibling), so differentiation is missing.

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?

Listing the eight analysis names implies which analysis to request, and the note about unverified fields returning 'unknown' sets expectations. But there is no guidance on when to choose this tool over basic_lookup/enriched_lookup/find_emails_batch, nor any exclusion condition, leaving usage to inference.

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