Ergora Specialists

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description goes beyond this by revealing that the tool queries a curated knowledge base of practitioners, books, and research and returns summarised, cited insights. This adds meaningful behavioral context without contradicting the 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?

The description is a single sentence with no filler. It front-loads the action and resource, then briefly enumerates the covered topics and the output type. Every phrase 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?

For a read-only, single-query tool with fully described parameters and no output schema, the description conveys the source domain and return shape (summarised, cited insights). Rate-limit details are already captured in the email parameter schema, so the description does not need to repeat them.

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 all three parameters thoroughly. The description adds marginal value by listing example topic areas for the query parameter, but it does not provide any additional parameter-specific 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 clearly identifies a specific action ('Ask') and resource ('Ergora Paid ads'), with explicit topic areas: Meta/Google/TikTok, creative, media buying, and attribution. It does not explicitly contrast with sibling specialists like ergora_marketing, but the topic list is enough to differentiate it in practice.

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 implied: the agent should ask this tool when the question concerns paid ads platforms or related topics. However, there is no explicit when-not-to-use guidance or recommendation of alternative sibling tools, leaving the decision 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 readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds the cross-vertical scope, but this is more about purpose than behavior. It does not disclose any additional behavioral traits such as rate limits, result aggregation format, or potential for large responses. With annotations covering the essential safety aspects, the description adds minimal behavioral context beyond the scope.

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 two sentences with zero redundancy. The primary purpose is front-loaded ('Ask across ALL 17 Ergora specialists at once'), followed immediately by usage guidance. Every word earns its place, making it highly efficient and scannable.

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 read-only query tool with no output schema, the description provides sufficient context to use it correctly: it defines the scope, clarifies when to use it, and the schema covers parameters. It does not describe the return format, but that is not strictly required given the tool's simplicity and the annotations' safety profile. The only minor gap is that it doesn't mention the optional 'vertical' restriction, but that is in the 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 100%, so every parameter (email, query, top_k, vertical) is fully documented in the input schema. The description adds no parameter-specific information, and since the schema already handles semantics, the baseline of 3 applies. No additional value is provided beyond what the schema gives.

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 ('Ask'), a specific resource ('ALL 17 Ergora specialists'), and a scope ('cross-vertical'). It also differentiates from sibling tools by explicitly naming the alternative pattern (ergora_<vertical>). An agent can immediately understand the tool's purpose and how it differs from the vertical-specific 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?

The description explicitly states when to use this tool ('when you don't know the domain') and when not to ('Use a specific ergora_<vertical> tool when you know the domain'). This provides clear decision criteria for an agent selecting between this tool and its siblings.

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=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, covering safety. The description adds that results are 'summarised, cited insights from a curated knowledge base,' which gives some context about output nature. However, it does not disclose any rate-limit behavior or other operational details beyond what the schema's email parameter hints at.

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 with no wasted words. It names the tool, its domain, and the output format efficiently.

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 simple query tool with one required parameter and no output schema, the description covers the essential function and result type. The email parameter's purpose is documented in the schema, which the agent can access. The description is adequate for an agent to understand how to invoke it, though it could mention the free-tier email behavior, but that is not essential for the core task.

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 three parameters (email, query, top_k) have descriptions. The tool description adds no parameter-specific meaning; it focuses only on the overall purpose. Per the calibration baseline, a score of 3 is appropriate when the schema already documents all parameters and the description does not need to compensate.

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 purpose: asking the Ergora Business strategy about competitive strategy, OKRs, planning, and positioning, and it returns summarised, cited insights from a curated knowledge base. This is a specific verb-resource pair and distinguishes it from sibling tools by naming the domain (business strategy) 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 description gives no guidance on when to use this tool versus alternatives. It does not mention other ergora_* tools or conditions for choosing this one over them. The sibling list is not referenced in the description, so an agent receives no routing context.

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 readOnly/openWorld/idempotent/non-destructive behavior. The description adds meaningful context beyond that: it discloses an answer style ('summarised, cited insights') and source scope ('curated knowledge base of leading practitioners, books and research'). No contradiction is 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?

Two sentences contain the action, domain scope, and return behavior with no filler. The most important query scope is front-loaded before the output description.

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 simple read-only research tool with one required natural-language parameter and no output schema, the description is complete: it says what to ask, what topics are in scope, and what kind of answer to expect. The absence of output schema is covered by the 'summarised, cited insights' clause.

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 explains query, email, and top_k thoroughly. The tool description adds no parameter-specific meaning, which is acceptable because the schema carries the full burden; 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?

The description names a specific action ('Ask') and resource ('the Ergora Community building ... knowledge base'), and further scopes it to brand communities, engagement, moderation, and events. It also states the output type (summarised, cited insights), making the tool's function clear and distinct from the other domain specialist 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?

The description gives clear topical context for when to use the tool via 'brand communities, engagement, moderation, events', so an agent can route community-building questions here. It does not explicitly name alternatives or exclusion conditions, but the sibling list and domain are enough to imply the boundary.

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 (readOnlyHint=true, destructiveHint=false, idempotentHint=true), so the bar is lower. The description adds useful behavioral context beyond that: it returns summarised, cited insights from a curated knowledge base of practitioners, books, and research. It does not discuss rate limits or output limitations, but the annotation coverage plus the added description make this solidly transparent.

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 with no filler. The first sentence front-loads the domain and action, and the second adds the key output characteristic (summarised, cited insights from a curated knowledge base). Every phrase 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?

For a read-only query tool with three parameters and no output schema, the description is sufficiently complete: it explains what kind of questions to ask and what kind of answer will come back. The schema handles parameter details and annotations handle safety, so the only real gap is the missing guidance about which sibling to prefer, which is already penalized in usage_guidelines.

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 parameters query, top_k, and email are already fully documented. The description itself adds no extra parameter meaning—only the word 'Ask' loosely maps to the query parameter. This matches the baseline of 3 for high 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?

The description clearly identifies the resource (Ergora Content marketing) and its scope (SEO, editorial, distribution, content strategy), and it states the output format (summarised, cited insights from a curated knowledge base). It does not explicitly distinguish itself from the broader ergora_marketing sibling, but the content-marketing scope narrows the purpose enough for an agent to select it for relevant queries.

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 guidance on when to use this tool versus the many siblings like ergora_ads, ergora_sales, or ergora_marketing. The description implies content-marketing questions are appropriate, but it does not state exclusions or point to an alternative, leaving the agent to infer the boundary based on the topic list alone.

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 tool safe and read-only. The description adds useful behavioral context by stating that it returns summarised, cited insights from a curated knowledge base, which helps an agent anticipate the nature and format of the response beyond what the schema 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?

Two concise sentences cover both the tool's purpose and its output style with no filler or repetition. The key scope information is front-loaded, making it easy for an agent to scan and understand 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?

For a simple query-and-answer tool with a clear schema and safe annotations, the description is sufficiently complete: it states what the user can ask, what topics are in scope, and what the response will look like. It doesn't need to explain return values in depth since the output format is briefly characterised.

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 explains query, email, and top_k. The description does not add parameter-specific meaning, but none is needed because each parameter, including the email free-tier detail, is well documented 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 identifies the tool as a question-answering resource for the creator economy, naming specific topic areas such as audience growth, monetisation, and personal brand. While it doesn't explicitly contrast with sibling specialists like ergora_content or ergora_marketing, the domain and output style make the purpose reasonably distinct.

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 to use the tool: when the user asks about creator-economy topics. However, it gives no explicit guidance on when not to use it or which sibling tool to prefer for overlapping topics like content or marketing, leaving the agent to infer boundaries.

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 read-only, idempotent, non-destructive behavior. The description adds beyond that by revealing the output style (summarised and cited) and the source (curated knowledge base of practitioners, books, and research), giving an agent a realistic expectation of what the call returns. No contradiction with 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?

The description is compact: two sentences, with the tool's role and domain front-loaded and the return type stated immediately. Minor grammatical awkwardness in 'Ask the Ergora Design & UX' but no unnecessary 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?

Given the tool's simplicity (three self-documenting parameters, no output schema, read-only annotations), the description covers the essential context: what to ask, what domain it covers, and what kind of response to expect. It does not mention the email-based rate-limit benefit, but that is already fully described in the 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 100%, so all three parameters (email, query, top_k) are fully documented in the schema. The description adds no further parameter-level detail, so the schema-coverage baseline of 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 identifies the tool as the Ergora Design & UX specialist and lists concrete subdomains (product design, usability, brand, design systems), with a clear retrieval action ('Ask') and expected output ('summarised, cited insights'). It does not explicitly contrast with sibling tools, but the domain list is enough for an agent to distinguish it from ergora_marketing or ergora_developer.

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 clear context for when to use the tool: any question about design, UX, usability, brand, or design systems. It does not explicitly state when not to use it or name alternatives, but the domain framing implies the appropriate routing and the sibling list makes exclusions inferable.

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=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, which cover safety and idempotency. The description adds that results are 'summarised, cited insights' but does not mention rate limits, authentication, or any behavioral side effects. With strong annotation coverage, the description adds limited extra behavioral context, so a 3 is appropriate.

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 immediately identifies the tool's action and domain, followed by the output type. It has zero filler words and effectively communicates the core purpose without 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?

For a simple query tool with three well-documented parameters and strong annotations covering safety and idempotency, the description is nearly complete. It lacks explicit mention of the email tier or rate limits, but these are covered in the parameter descriptions. The absence of an output schema is fine since the description states the return type (summarised, cited insights). Overall, nothing critical is missing 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 coverage is 100%, so all parameters (query, email, top_k) have detailed descriptions. The tool description adds no additional parameter information beyond what the schema provides. The baseline of 3 applies because the schema fully documents the parameters, and the description does not need to compensate.

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 function: 'Ask the Ergora Developer / engineering' with explicit domain areas (software craft, DevOps, architecture) and specifies the output (summarised, cited insights from a curated knowledge base). It distinguishes itself from the sibling tools by naming the engineering domain, which is absent from the sibling names.

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 implicitly guides usage by specifying the engineering domain, making it obvious when to use this tool over siblings like ergora_marketing or ergora_sales. It does not explicitly state 'use for engineering questions' or list exclusions, but the domain is clearly defined and the sibling list makes the differentiation apparent.

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 mark the tool as read-only, idempotent, and non-destructive. The description adds useful behavioral context by stating it returns summarised, cited insights from a curated knowledge base, which goes beyond the structured 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?

The description is a single, well-structured sentence that front-loads the domain scope and then states the return value. There is no redundant or filler content.

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 simple ask-and-return tool, the description is complete enough: it states the domain, the source, and the output format. The schema covers parameters, and annotations cover safety traits, so 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 the schema already documents all three parameters. The description does not add extra parameter-level meaning beyond the general 'ask a question' framing, so the baseline of 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 clearly states the tool is an ecommerce specialist covering Shopify/WooCommerce/DTC, conversion, retention, and email/SMS, and that it returns summarised, cited insights. This distinguishes it from sibling domain specialists like ergora_ads or ergora_marketing by naming its specific focus.

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 gives clear context for when to use it: ecommerce-related questions in the listed domains. It does not explicitly name sibling alternatives or exclusions, but the domain list makes the intended use obvious.

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, openWorld, idempotent, and non-destructive behavior. The description adds useful behavioral context by explaining that results come from a curated knowledge base of practitioners, books, and research and are returned as summarised, cited insights. It does not contradict the annotations and provides value beyond them.

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 front-load the core domain and topic scope, then describe the output format. Every sentence earns its place with no filler or 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?

Given the robust annotations, complete parameter schema, and a simple research-query tool, the description includes everything an agent needs to select and call it correctly: what topics it covers and what kind of response to expect. The lack of an output schema is mitigated by the explicit 'summarised, cited insights' phrasing.

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 (email, query, top_k) are already documented structurally. The description adds no parameter-level detail beyond the task context, which is acceptable given the baseline for high 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?

The description states exactly what the tool does: answer entrepreneurship questions covering starting, validating, funding, and scaling a business by returning summarised, cited insights from a curated knowledge base. This clearly distinguishes it from the many sibling specialist tools by scoping it to the entrepreneurship domain.

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 clear usage context by enumerating the business lifecycle topics the tool covers (starting, validating, funding, scaling), so an agent can match user intents to this specialist. It doesn't explicitly state when not to use it or name alternatives, but the domain framing is strong enough without exclusions.

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 (readOnlyHint, idempotentHint, openWorldHint, non-destructive). The description adds value beyond this by disclosing the output behavior: 'Returns summarised, cited insights from a curated knowledge base of leading practitioners, books and research.' This sets accurate expectations for answer format and sourcing, which annotations alone would not convey. No contradiction with 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 sentences with zero waste. The first sentence front-loads the verb and topic scope; the second adds return format and knowledge source. Every phrase earns its place, and the most decision-relevant information (what to ask about) comes first.

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 moderately simple tool (3 params, 1 required, no output schema), the combination of description, schema, and annotations is nearly complete: description covers purpose/topics/output format/sources, schema fully documents params and email behavior, and annotations cover safety. The main gap is the absence of an output schema, so return-structure expectations rest on the brief 'summarised, cited insights' phrase, and sibling routing 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 description coverage is 100% — all three parameters (email, query, top_k) have rich descriptions, including the email quota distinction (30 vs 5 queries/day) and the 'ask the user once, then pass it on every call' guidance. The description adds no parameter-specific meaning beyond this; the schema does the heavy lifting, 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?

The description states a clear verb+resource ('Ask the Ergora Business finance') and enumerates its scope: SaaS metrics, cash flow, valuation, fundraising, CFO. This distinguishes it from most siblings (marketing, sales, HR, legal, etc.). However, it does not explicitly differentiate itself from ergora_ask (the generic ask tool) or ergora_business_strategy, leaving some ambiguity among closely related specialists.

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 topic list (SaaS metrics, cash flow, valuation, fundraising, CFO) implies when to use this tool: finance-domain questions. But there is no explicit when-not-to-use guidance, no named alternatives, and no routing hints among the 18 siblings. An agent must infer that non-finance questions belong elsewhere.

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, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context by specifying that results are summarised, cited insights drawn from a curated knowledge base of practitioners, books, and research, which helps set expectations about answer format and sourcing.

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, tightly written sentence that leads with the action and resource, names the domain topics, and then states the output format. Every phrase contributes value, with no filler or redundant restatement of 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 simple Q&A tool with rich annotations and complete schema descriptions, the description covers the essential context: what to ask, what domain it covers, and what kind of response to expect. Since there is no output schema, the explicit mention of summarised, cited insights is important and sufficient for an agent to understand the return style.

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 (query, email, top_k) already have meaningful schema descriptions. The tool description itself adds little parameter-level detail beyond the general 'ask a question' framing, so the baseline score of 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 uses a clear verb ('Ask') with a specific resource (Ergora HR & people ops) and lists the covered topics: hiring, culture, performance, employment. It also states the output type: summarised, cited insights. It does not explicitly contrast itself with generic siblings like ergora_ask or list_specialists, but the HR domain focus is enough to separate it from the other domain specialists.

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 to use the tool: for HR and people-ops questions about hiring, culture, performance, or employment. However, it provides no explicit guidance on when not to use it or which sibling tool to choose instead, such as ergora_ask for general questions or other specialists for different domains.

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, openWorld, idempotent, and non-destructive hints. The description adds that it returns 'summarised, cited insights from a curated knowledge base', which is useful context about output nature. No contradiction with annotations; the addition is modest but meaningful.

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, concise sentence that front-loads the primary action ('Ask') and domain, then describes the output. It avoids fluff and is well-structured for quick parsing by an agent.

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 Q&A tool with three parameters and no output schema, the description provides sufficient context: it states the domain, the output format (summarised, cited insights), and the knowledge base origin. It does not explain return value details, but that is acceptable given the absence of an output schema and the simplicity of the 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 coverage is 100% (all parameters have descriptions), so the schema already documents query, email, and top_k semantics. The description does not add any parameter-level detail beyond the schema, so a baseline of 3 is appropriate. No compensation needed.

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 is for asking about leadership and management (teams, execution, feedback) and that it returns summarised, cited insights from a curated knowledge base. The verb 'Ask' and the domain differentiation from sibling tools (e.g., ergora_marketing, ergora_finance) are clear, though it could tighten the differentiation edge.

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 usage for leadership/management topics via the domain phrase, but it does not explicitly say 'use this for leadership questions instead of other specialists' or provide exclusion criteria. Sibling names make the domain obvious, but explicit when-to-use guidance is absent, leaving some inference to the agent.

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, idempotentHint, and non-destructive behavior. The description adds meaningful behavioral context: outputs are summarised, cited, sourced from a curated knowledge base, and explicitly not legal advice—an important expectation-setting disclosure for an agent.

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 sentence packs domain scope, output format, source, and disclaimer with no filler. It is front-loaded with the action and domain before the return details.

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 simple tool with one required parameter, full schema coverage, and read-only annotations, the description is complete: an agent knows what to ask, what it returns, and the legal-advice boundary. No output schema is present, but the return description is sufficient 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%, with all three parameters already well described in the input schema. The description reinforces that query is natural-language but adds no parameter-level meaning beyond what the schema 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 states a specific purpose: answering legal research questions on contracts, IP, compliance, and startup law. It also names the output form—summarised, cited insights from a curated knowledge base—and clearly distinguishes the tool from sibling ergora_* specialists by domain.

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 topic list and 'Business legal' framing make when-to-use clear relative to sibling specialists like ergora_finance or ergora_marketing. It does not explicitly name alternatives or exclusion conditions beyond 'not legal advice,' so routing guidance is clear but not fully explicit.

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=true, idempotentHint=true, and destructiveHint=false, so safety is covered. The description adds the fact that there are exactly 17 verticals and that it returns coverage details, but it does not disclose output format or other behavioral aspects. Given the strong annotation coverage, this is sufficient.

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, concise sentence with no fluff. It front-loads the verb 'List' and immediately specifies the resource and scope.

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, no output schema, and rich annotations, this description is complete. It tells the agent exactly what the tool returns (the 17 verticals and what each covers), which is all that is needed 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?

There are zero parameters, so the description does not need to explain any. The baseline for 0 parameters is 4, and there is nothing to compensate for.

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 (List), a specific resource (the 17 Ergora specialist verticals), and what the tool does (covers what each covers). It clearly distinguishes this meta-listing tool from its siblings, which are the actual specialist 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?

There is no explicit guidance on when to use this tool versus directly calling a specific specialist. The description is purely descriptive and does not mention alternatives, prerequisites, or exclusions, leaving the agent to infer usage from context.

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 readOnly, openWorld, idempotent, and non-destructive behavior. The description adds useful return-style detail: summarised, cited insights from a curated knowledge base of practitioners, books, and research. It does not cover rate limits, but the email parameter schema covers tier access, and there is 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 compact sentences with each clause adding distinct value: domain scope, source type, and output style. No filler, and the content is 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?

For a read-only knowledge specialist with three well-documented parameters, the description covers purpose, domain scope, and return shape (summarised, cited insights). The lack of an output schema is partly mitigated by the explicit return description; an explicit rate-limit or sourcing caveat would be a small improvement.

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 fully documents query, email, and top_k. The description only implies that query is a natural-language marketing question and adds no format, default, or constraint details beyond the schema, 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?

States a specific action ('Ask') and a named specialist, scoped to local SEO, small-business marketing, and community presence. This distinguishes it from generic ergora_marketing and other siblings, though it does not explicitly name 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?

The topic phrase implies when to use it — for local marketing questions — but there are no explicit 'use this instead of ergora_marketing/ergora_community' instructions or exclusions. An agent can infer the domain but gets no routing guidance among the many related siblings.

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=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false, covering safety. The description adds that insights are 'summarised, cited' and drawn from a curated knowledge base, which is useful context beyond the annotations, but does not deeply elaborate on return formatting or limitations. With annotations covering the safety profile, a 3 is appropriate.

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 immediately states the tool's purpose and scope. No filler, and the key terms (Marketing fundamentals, positioning, strategy, growth, analytics) are placed at the beginning. 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 simple Q&A tool with only one required parameter and 100% schema coverage, the description is largely sufficient. It clarifies the knowledge domain and output format (summaries with citations). However, it could briefly mention that it is not for advanced or bespoke marketing tactics, but this is a minor gap. Overall, an agent can call it correctly without missing essential details.

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 three parameters (email, query, top_k) are fully documented in the schema. The description does not add additional meaning beyond what the schema provides. Baseline of 3 applies because the schema carries the full burden.

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 ('Ask'), a resource ('Ergora Marketing fundamentals'), and a scope ('positioning, strategy, growth, analytics'). It clearly distinguishes from sibling specialist tools by naming the marketing domain and the nature of output ('summarised, cited insights'). An agent can confidently identify it as a marketing knowledge Q&A tool.

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 usage for marketing fundamentals questions but does not explicitly compare against alternatives like ergora_business_strategy or ergora_sales. No when-to-use vs. when-not-to-use guidance is provided; the domain name alone signals applicability, but exclusions are absent.

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=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds behavioral detail: it returns summarised, cited insights from a curated knowledge base, and implies a research-oriented, non-mutating operation. This goes beyond the annotations without contradicting them.

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 sentence that front-loads the action ('Ask') and the subject ('Ergora PR & communications'), then lists specific topic areas and describes the output. It is concise, informative, and avoids any fluff or 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 Q&A-style tool with simple parameters and no output schema, the description is largely complete. It explains what the tool does, the domain, and the nature of the output. It does not mention rate limits or the email parameter, but those are already detailed in the schema. The description could optionally hint at use cases, but it is not missing critical information 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?

The input schema has 100% description coverage for all three parameters (query, top_k, email), so the schema fully documents them. The description adds no additional parameter-specific semantics, so the baseline of 3 applies. It does not compensate for any coverage gap because none exists.

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 identifies the tool as a PR & communications specialist with a specific verb ('Ask') and resource (PR & communications). It lists the domain areas (media relations, crisis comms, brand reputation) and states the output (summarised, cited insights from a curated knowledge base). This distinguishes it from other er gor a_* specialists by domain.

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 usage for PR-related questions through its title and content, but it does not explicitly state when to use this tool versus alternatives. It does not mention any exclusions or alternative specialists, nor does it provide guidance on routing based on topic. The usage context is clear but not explicit enough for a 4 or 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 cover readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds useful behavioral context beyond those: the tool returns 'summarised, cited insights' and draws from a 'curated knowledge base of leading practitioners, books and research.' This clarifies the answer style and source boundary without contradicting the 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 sentences with no filler: the first defines the tool's domain, the second defines its output and knowledge source. Every phrase contributes value, and the description is front-loaded with the primary action ('Ask').

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 simple read-only knowledge-retrieval tool with one required parameter and three fully documented parameters, the description is complete. It states what the tool returns and from what knowledge source, while annotations cover safety and idempotency. Nothing needed to invoke it successfully 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%; the input schema already documents query, email, and top_k, including defaults, bounds, and the email quota-unlock behavior. The description adds no per-parameter meaning beyond the sales domain, so it meets but does not exceed the baseline for a fully covered 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 identifies the tool as a sales-domain specialist ('Ask the Ergora Sales') and enumerates concrete sales subdomains ('prospecting, outreach, pipeline, closing, sales ops'). It also states the output format ('summarised, cited insights'), so an agent can distinguish it from sibling tools like ergora_marketing or ergora_ads without opening their definitions.

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 sales-scoped topic list provides a clear implicit usage condition: use this tool for sales-related questions. It does not explicitly name alternatives or when-not-to-use conditions, so it stops short of a 5, but the domain context is strong enough for an agent to select it appropriately among siblings.

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