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

Annotations already indicate read-only, idempotent, non-destructive behavior. Description adds credit cost details and response structure (two lists, pagination), going beyond 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?

Four well-structured sentences, no fluff, front-loaded with purpose, followed by response details and cost guidance.

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 purpose, filter options, response format, credit cost, and references sibling tools. Adequate for a complex search tool with 12 parameters and 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?

Schema description coverage is high (75%), and the tool description does not significantly add meaning beyond what the schema already provides for parameters.

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?

Clearly states it discovers companies via multiple filters (keyword tags, name, location, employee ranges, revenue, domains, tech stack). Distinct from sibling enrichment and people search tools.

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?

Explicitly advises using apollo_org_enrich for detailed data, warns about credit cost per page, and recommends confirming costs before multi-page batches.

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, openWorldHint, idempotentHint, destructiveHint false. Description adds that it 'consumes no credits' and requires a master API key, and clarifies what it cannot do (credit balance). No contradictions; adds valuable context beyond 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?

Three sentences with zero waste. Purpose is front-loaded. Each sentence adds distinct value: purpose, usage guidance, and limitation/alternative. Highly efficient.

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 tool with no parameters and no output schema, the description covers key information: what it reports, when to use, prerequisites, and what it cannot do. Annotations provide additional safety signals. Slightly more detail on the output format (e.g., what fields are in the headers) could be added, but overall 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?

Input schema has zero parameters, so baseline is 4. Description adds meaning by explaining what the tool returns (rate limit headers, per-endpoint usage). While no parameter details are needed, the description provides context about the output, which is sufficient.

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?

Description clearly states 'Report per-endpoint Apollo API usage against the minute/hour/day rate limits, plus the most recent rate-limit headers observed.' This specifies a specific verb ('Report') and resource ('API usage / rate limits'). It distinguishes from sibling tools which are all search/enrich operations.

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?

Explicitly states when to use: 'Use before large batches to check headroom, and to answer "how much have we used?"' Also provides exclusion: 'Note: Apollo exposes no API for the remaining credit balance — that is only visible in the Apollo UI.' Prerequisites are given: 'Requires a master API key; consumes no credits.'

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?

Description adds credit consumption cost ('Consumes 1 credit when a record is enriched') beyond annotations. Annotations already indicate read-only, idempotent, non-destructive behavior. No contradictions present.

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 with no waste: first sentence lists output fields, second gives input requirements, third covers cost, fourth provides alternative. Purpose is front-loaded and structure is clear.

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 key aspects: purpose, input requirements, credit cost, and alternative guidance. Could be improved by describing return format or error behavior, but given the annotations and listed fields, it is fairly complete for an 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?

Description adds the constraint that at least one of domain, name, website, or linkedinUrl is required, which is not enforced in the schema (0 required params). It also mentions the 'fields' parameter for projection. With 40% schema coverage, this compensates well.

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?

Description clearly states the tool fetches full firmographics for one company via Apollo and lists specific fields (industry, keywords, employee count, etc.). It distinguishes from siblings by referencing the Lassox MCP for Danish companies, indicating use for non-DK or Apollo-specific needs.

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?

Explicitly provides when to use this tool vs. the Lassox MCP for Danish companies, and states required identifiers ('Provide at least one of domain, name, website, or linkedinUrl'), giving clear context and an alternative.

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 significant behavioral context beyond the annotations: it consumes credits, applies reveal flags to every person, requires webhookUrl for phone reveal, respects Apollo's hard rate limit (20/min), and emits MCP progress notifications. Annotations (readOnlyHint, idempotentHint, destructiveHint) are consistent and the description enriches them with operational details.

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 moderate in length (few sentences) and front-loads the main action. Each sentence adds necessary detail (chunking, concurrency, retry, credit consumption, rate limits, progress notifications). Some redundancy exists (e.g., 'bounded concurrency' and explicit concurrency parameter), but overall efficient for the tool's complexity.

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 no output schema, the description fully specifies the return format: { total, succeeded, failed, creditsConsumed, requestIds, results[] } with input order. It covers all behavioral aspects (rate limits, credit cost, per-item isolation, progress notifications). For a tool with 6 parameters, concurrency, and multiple constraints, this is exceptionally 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% (all 6 parameters have descriptions), so baseline is 3. The description adds value by: clarifying credit consumption tied to reveal flags, explaining that results preserve input order, and noting that revealPhoneNumber requires webhookUrl (already in schema but reinforced). It also mentions progress notifications related to progressToken, which is not in 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?

The description clearly states 'Enrich up to 100 people via Apollo in one call,' specifying the verb (enrich), resource (people), and scope (up to 100). It distinguishes itself from siblings like apollo_person_enrich (single person) and apollo_people_search (search) implicitly through the batch nature.

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 provides explicit usage guidance: churns into bulk_match calls, fans out with bounded concurrency, retries HTTP 429, isolates per-item failures, and warns about credit consumption and rate limits. It advises confirming total credit cost with the user. However, it does not explicitly state when not to use this tool or compare directly to alternatives, but the context is clear enough for selection.

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 indicate readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false. The description adds crucial behavioral context: results are intentionally slim with obfuscated last names and no email/phone numbers, and it explicitly warns against looping for contact data. This goes beyond annotations to prevent misuse.

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 3-4 sentences, front-loaded with the core purpose, then cost/API key requirement, then behavioral limitations and forwarding guidance. Every sentence adds value without redundancy or fluff, making it easy for an agent to parse quickly.

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's complexity (14 parameters, no output schema), the description covers purpose, usage guidelines, and key behavioral traits. It provides sufficient context for the agent to avoid common pitfalls. However, it could be more complete by mentioning pagination parameters or the fields projection feature, which are in the schema but not summarized.

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 description mentions high-level filter categories (title, seniority, location, employer domain/id, employer size) which map to some of the 14 parameters, but does not detail specific parameters like page, fields, perPage, qKeywords, revenueRange, etc. With schema description coverage at 36%, the description partially compensates but leaves many parameters unexplained, limiting the agent's ability to use them effectively.

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 immediately states 'Find people via Apollo' with specific criteria (title, seniority, location, employer domain/id, employer size), clearly distinguishing it from sibling tools like apollo_companies_search. The verb 'find' and resource 'people' are explicit, and the later guidance to use apollo_person_enrich for contact data reinforces its unique purpose.

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 explicitly states it is FREE (no credits) but requires a MASTER Apollo API key, providing cost and auth context. It further advises against looping for contact data and directs the agent to use apollo_person_enrich instead, giving clear when-to and when-not-to usage 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?

Beyond annotations (readOnlyHint, idempotentHint), the description discloses critical behaviors: credit consumption per enrichment, extra cost per email/phone reveal, async phone delivery via webhookUrl, GDPR restrictions on personal emails, and the user's responsibility as data controller. This adds substantial value beyond the annotation hints.

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 entire description is a single, dense paragraph that front-loads the purpose, then efficiently covers key behaviors in separate sentences. No redundant information; every sentence adds value. The structure uses capitalization and punctuation effectively to highlight important warnings.

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 13 parameters and no output schema, the description comprehensively addresses credit usage, async phone retrieval, and GDPR concerns. It lacks specifics on the return format (e.g., what fields the profile contains) but the tool's purpose of returning 'full profile' is clear. The description is thorough enough for an AI agent to handle common scenarios.

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 low (38%), and while the description explains revealPhoneNumber, webhookUrl, and their credit implications, it does not detail most parameters (name, email, domain, etc.). The meaning of these is inferable from context but not explicitly stated, leaving a gap in parameter understanding.

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 clearly states the tool's core action: 'Match one person via Apollo and return their full profile (employment history, employer, departments, seniority).' The verb 'match' and 'return' paired with the resource 'person profile' precisely defines the purpose, distinguishing it from search tools (apollo_people_search) that list many results.

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 notes credit consumption and extra costs for reveal options, implicitly guiding when to use (when a full profile is needed) and cautioning about cost. It does not explicitly list alternatives or when not to use, but the context of credit consumption and async phone delivery provides practical 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, openWorldHint, idempotentHint, destructiveHint. Description adds that it provides 'capabilities and examples', which is behavioral context beyond 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?

Two concise sentences that front-load purpose and usage. Every sentence adds value with no 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?

No output schema, so description should clarify return structure. It mentions 'capabilities and examples' but not format. For a simple search tool, it is adequate but leaves some ambiguity.

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 0%. Description does not explain the two parameters (query and limit) beyond their schema types. With no explanation, an agent may not know how to use them effectively.

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?

Clearly states 'Search the Apollo MCP server capabilities and examples'. Differentiates from sibling tools by advising to use it first when deciding which tool to call.

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?

Explicitly says 'Use this first when deciding which Apollo tool to call', providing clear guidance on when to use. Does not explicitly exclude scenarios but context implies it is a discovery 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?

Annotations indicate readOnlyHint, openWorldHint, idempotentHint true, and destructiveHint false. The description adds valuable behavioral info: free (no credits), 30-day retention, and specific retry-on-404 behavior. No contradiction.

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 sentences, each essential. First sentence conveys purpose and condition; second adds cost and retry policy. No filler, efficiently front-loaded.

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 annotations and schema richness, the description adequately covers asynchronous nature, retry handling, and retention. Lacks detail on successful response structure, but rules state no output schema needed for return values; still, a minor 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 coverage is 100%, providing a baseline of 3. The description adds context: requestId comes from apollo_person_enrich or apollo_people_bulk_enrich and may be negative, which aids correct parameter usage.

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 clearly states the tool fetches results of an asynchronous Apollo enrichment (phone-number reveal or waterfall) using a request_id, with the specific use case of recovering a missed webhook callback. This distinguishes it from sibling tools like apollo_person_enrich which initiate enrichment.

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 explicitly says to use this tool when a webhook callback was missed and provides retry guidance: a 404 with retry_after_seconds means not ready. It lacks explicit alternatives or when-not-to-use, but the context is clear enough.

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