SOMA Brewing Company

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

With no annotations, the description carries the full transparency burden. It details what information is retrieved (pricing tiers, keg/draft options, tasting booking) and assumes no side effects. This is adequate for a read-only tool, though it does not mention auth requirements or response format.

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 efficiently conveys the tool's purpose, target audience, and contents. No filler words; every component serves a purpose. Front-loaded with the core offering.

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 parameters and no output schema, the description adequately covers the tool's returned information. It lists key content areas (pricing, keg options, tasting booking). Slightly lacking in specifying output format, but acceptable for a simple retrieval 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?

Input schema has zero parameters, so schema coverage is 100% trivially. Baseline for 0 params is 4. The description adds no parameter information, which is acceptable since there are none to document.

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 provides B2B pricing tiers, keg/draft options, and how to book a tasting for restaurants, bars, hotels, and events. It uses specific verb 'get' and resource 'wholesale info', distinguishing it from sibling tools like get_pricing_and_delivery which likely covers general pricing.

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 business customers needing wholesale pricing or keg options. It provides clear context but does not explicitly state when not to use it or mention alternatives. However, the target audience and purpose are well-defined, guiding appropriate invocation.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only says the tool returns a 'detailed spec' for a single beer, but does not describe what happens for unknown slugs, what fields the spec contains, or whether the operation is read-only.

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 one compact sentence with no filler. The core operation is front-loaded and the slug list is a useful quick reference.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter lookup tool, the description and schema together give enough information for an agent to select and invoke it correctly. The main gap is the lack of output-shape or error-behavior details, but the tool is simple enough that this is not critical.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the slug parameter is fully documented with an enum and description. The description's slug list duplicates the schema without adding extra meaning or syntax details, so the baseline of 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 specific verb and resource: 'Detailed spec for a single beer by slug.' It is clearly distinct from siblings like list_beers by specifying a single beer and enumerating the valid beer types.

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 tool is for retrieving one specific beer by slug, but it does not explicitly contrast it with list_beers or other get_* tools. There is no when-to-use/when-not-to-use 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?

No annotations are provided, so the description carries the full burden of disclosure. It clearly lists the types of information returned (taglines, founder, location, contact details, social handles, and the 2026 pivot). For a read-only brand overview, this is transparent enough, though it does not mention rate limits or authentication requirements, which are not critical for this tool.

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 is moderately long due to enumerating the specific elements covered. It is front-loaded with 'Brand overview' and conveys the main purpose efficiently. Minor improvement could be splitting into two sentences for readability, but it remains concise.

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 that there are no parameters, no output schema, and a straightforward purpose, the description comprehensively covers the tool's scope. It includes the unique and potentially important context of the 2026 pivot, which helps the agent understand the relevance 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?

There are no parameters, so the baseline score is 4. The description does not need to explain parameter semantics, and it correctly focuses on the output content. The input schema already indicates no parameters, so no additional information is required.

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 provides a brand overview including specific elements like taglines, founder, location, contact details, social handles, and the 2026 pivot. This distinguishes it from sibling tools that focus on individual beers (get_beer), brewing process (get_brewing_process), or other specific aspects.

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 tool for brand-level information, but it does not explicitly mention when to use it versus alternatives such as get_beer or get_faq. Given the number of sibling tools, explicit guidance would improve clarity, but the context is sufficient for basic usage.

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?

With no annotations, the description is the only source of behavioral disclosure. It only lists content topics and does not describe return format, read-only nature, permissions, rate limits, or any side effects. While it does not contradict annotations (there are none), it fails to provide meaningful behavioral context beyond what the name implies.

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 wasted words. It front-loads the 'six-step production process' and then lists the specific components, making it easy to parse. The parenthetical enumeration is dense but acceptable for a content summary.

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 parameterless informational tool with no output schema, the description covers the subject matter comprehensively by naming the main content areas: production steps, ingredients, and certifications. It does not explain the return shape or how it relates to sibling tools, but these are less critical given the simple nature and low complexity 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?

The input schema has zero parameters, so the baseline is 4. There are no parameter meanings to clarify, and the description does not need to compensate for any schema gaps. The content summary is sufficient for calling a parameterless tool.

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's subject matter: the brewing process, including specific production steps, ingredient sourcing, and certifications. Though it lacks an explicit verb like 'returns' or 'retrieves', the title and the tool name make the purpose unmistakable, and it is distinct from siblings like get_beer or get_brand.

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 offers no guidance on when to use this tool versus its alternatives. It does not mention any specific conditions, exclusions, or related tools, leaving the agent to infer usage solely from the name and content summary.

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?

With no annotations provided, the description carries the full burden—and it delivers. It discloses the pre-order status, shipping timeline, the two possible return behaviors (cart permalink vs. product page), and that the tool never charges anyone. This is exemplary transparency for a side-effecting purchase tool.

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 appropriately sized and front-loaded with the most important fact ('Builds a direct buy link'), followed by the critical pre-order caveat. Every sentence earns its place; the length is justified by the operational warnings and return-behavior distinctions.

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?

Despite having no output schema, the description fully explains what the agent can expect: a cart permalink if variant IDs are configured, otherwise a product page. It also covers the important user-facing caveats and payment model. Nothing essential for correctly invoking and presenting this tool 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 baseline is 3. The description adds useful behavioral context about 'pre-filled checkout' and variant IDs, but it doesn't explain the input parameters themselves beyond what the schema already documents. The schema handles parameter semantics adequately.

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 specific verb ('Builds') and a clear resource ('direct buy link an agent can hand to the user'). It clearly distinguishes this tool from the sibling get_* tools by focusing on the checkout/purchase-link action, so an agent can select it without ambiguity.

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 the tool and even instructs the agent to disclose the pre-order status. It does not explicitly name alternative tools or when-not-to-use conditions, but the use case is specific enough that this is a minor gap rather than a fatal one.

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?

With no annotations, the description carries full burden but only lists topics. It lacks disclosure of read-only nature, auth requirements, or return format. Assumes safe use but provides no behavioral context.

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

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

Single sentence, front-loaded with key phrase 'All customer FAQs'. Efficiently lists topics without extra filler, but could be broken into bullet points for clarity.

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 parameters and no output schema, the description is the sole source of information. It covers content but not format (e.g., list of Q&A pairs) or how to use it for specific queries. Adequate but not rich.

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?

No parameters exist, so baseline is 4. The description adds meaning by detailing the FAQ content areas, which compensates for the lack of 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 that the tool returns all customer FAQs and lists specific topics (SOMA, ABV, etc.), making it distinct from sibling tools that focus on single aspects. However, it does not explicitly state the verb 'get' or 'retrieve', though it's implied.

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 use this tool versus specialized siblings like get_pricing_and_delivery or get_brewing_process. The description does not mention that this is a general overview and that specific tools provide more detail.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It explains the output content and units but says nothing about response format, pagination, authentication, read-only safety, or behavior when slug is omitted. The read-only nature is only inferred from the tool name and domain, not disclosed.

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

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

The description is a single, front-loaded sentence with no filler. Every clause adds concrete information about the data returned, target audience, and measurement units.

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 endpoint with one optional parameter and 100% schema coverage, the description is nearly complete: it specifies the output fields and units, and the schema covers the slug behavior. Missing are explicit routing to alternatives and a light note on response packaging, but these are minor for this 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?

There is only one optional parameter, and the schema description covers it fully, including the omit-for-full-lineup behavior. The tool description adds no parameter-specific semantics beyond what the schema already provides, so the baseline score of 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 clearly states what the tool returns: structured, machine-readable nutrition data per beer, and it enumerates the exact fields and units (per-can and per-100ml calories, carbs, protein, sugar, ABV, allergens, dietary flags). The health-platform framing also helps differentiate it from general beer-info siblings such as get_beer and list_beers.

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 use when a caller needs nutrition data for health, fitness, or diet-tracking platforms, but it does not explicitly state when to prefer this tool over siblings like get_beer or list_beers, nor does it mention exclusions or alternatives. Usage context is present but left to inference.

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

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

With no annotations present, the description carries the full burden, and it does well by disclosing that this is 'non-commercial,' that there is 'never a cash deal,' and by outlining the standard offer (cooler, Founding Fifty codes, optional co-created content). It does not mention response format or possible routing limitations, but for a read-only info tool the key behaviors are 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 purposeful sentences: the first scopes the audience and program type, the second details the offer and the crucial sibling distinction. No wasted words, and the most decision-relevant contrast appears at the end for easy reference.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter informational tool with no output schema, the description covers what the program is, who it is for, what is offered, what is excluded, and how it differs from the nearest sibling tool. An agent has enough context to select and invoke this tool correctly without further clarification.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so there is nothing for the description to explain. The baseline for zero-parameter tools is 4, and the description correctly focuses on purpose and usage rather than inventing parameter details.

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 a specific resource ('non-commercial partnership program') with a clear verb ('get... info'), names target audiences (fitness/sports communities, venues, press), and explicitly contrasts with get_b2b_wholesale. This makes it immediately distinguishable from its sibling 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?

It explicitly states when to use this tool versus the key alternative: 'Distinct from get_b2b_wholesale, which is a paid commercial arrangement for venues.' This gives the agent a concrete decision rule between non-commercial partnership inquiries and paid commercial venue deals.

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?

No annotations are provided, so the description must carry the full behavioral burden. It describes the returned content but does not explicitly state that it is a read-only lookup, has no side effects, or that the data is static. The 'get_' prefix and content imply safety, but explicit disclosure is absent.

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 dense sentence containing all key facts, but it is efficient and front-loaded with the most important pricing data. It could be structured with bullets for readability, but it avoids waste and stays within a reasonable length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no parameters, the description fully explains what the tool returns: prices, delivery cities, and the delivery fee. Nothing an agent needs to call or interpret the result 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?

The tool has zero parameters, so the schema is trivially 100% covered. The description adds no parameter details because none exist, which is appropriate. Baseline of 4 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 exactly what the tool returns: specific launch prices for beer packs, delivery cities, and the flat delivery fee. It clearly distinguishes itself from siblings like get_beer or get_buy_link by covering pricing and logistics details.

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 clearly implies when to use it (whenever pricing or delivery info is needed) but does not explicitly name alternatives or exclusions. Since no sibling tool covers the same scope, the implied context is sufficient.

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?

No annotations are provided, so the description carries full burden. It describes the output (recipes and pairings) but does not explicitly state that the tool is read-only, safe, or free of side effects. However, the content strongly implies a read operation with no destructive effects.

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 key deliverables (cocktail recipes, ingredients, method, food pairings). Every part is informative and no words are 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's low complexity (no parameters, no output schema, no annotations), the description adequately covers what the tool returns. It could be slightly more explicit about the scope (e.g., all available recipes), but it is complete enough for an agent to use 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?

The input schema has zero parameters, so the description does not need to add parameter-level detail. The description is consistent and sufficient for a parameterless tool.

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 returns non-alcoholic beer cocktail recipes (with examples) and food pairing guides. It distinguishes itself from sibling tools like get_beer and get_brewing_process by focusing on recipes and pairings rather than beer properties or production.

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 by the name and description: call this tool when you need recipes or food pairings for non-alcoholic beer. No explicit alternatives or when-not-to-use guidance is provided, but the context of sibling tools makes the distinction clear.

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?

No annotations are provided, so the description carries the full burden. It mentions free delivery and pause-anytime, which are behavioral traits, but does not disclose auth needs, rate limits, or return format. For a read-only query, this is minimally adequate.

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 key information is front-loaded in the first sentence, and the second adds a beneficial detail. Every word 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?

Given the lack of output schema and zero parameters, the description is fairly complete. It covers the main aspects of what the tool returns. It could be slightly improved by mentioning the response format or how to handle errors, but it is sufficient for the tool's simplicity.

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 no parameters, so the schema provides no information. The description adds meaning by listing what the tool returns (pricing, perks, etc.), which is valuable beyond the empty 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 retrieving the three monthly beer subscription tiers with pricing, savings percentage, and included perks. It specifies the exact resource and details, distinguishing it from sibling tools like get_pricing_and_delivery or get_b2b_wholesale.

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 the tool is for monthly subscription plans, but it does not explicitly state when to use this tool versus alternatives like get_pricing_and_delivery or get_b2b_wholesale. No exclusions or alternative guidance is provided.

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 fully discloses the tool's behavior: it is read-only, cannot move or spend coins, requires a short-lived token from the user, and returns a specific error message for invalid tokens. This is comprehensive given no annotations are provided.

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 extremely concise, using three sentences to cover purpose, usage instructions, and error handling. It is front-loaded with the core functionality and avoids any 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?

There is no output schema, but the description specifies the return expectation (balance plus expiring coins summary and error object for invalid tokens). It covers the authentication mechanism, error recovery, and the tool's limitations, making it fully complete for an agent to select and invoke 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?

The single parameter 'wallet_token' is already documented in the schema, but the description adds crucial context: how to obtain it (user must generate in the app), its expiration (~10 minutes), and what to do if it's invalid. This adds significant value beyond 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 it is a read-only wallet summary for SOMA Coins, including balance and expiring coins. It distinguishes itself from siblings by emphasizing it cannot claim or redeem coins, and that there are no such tools available, making its purpose unambiguous.

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 explicitly instructs the agent to ask the user for a wallet token generated in the app, notes the token expires in ~10 minutes, and explains the expected behavior when the token is invalid. It also clarifies it should not be used for claiming or redeeming coins, providing clear usage 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?

No annotations provided, so description fully carries burden. Discloses idempotency ('signing up twice never double-sends') and side effects (CRM storage, welcome email). Does not mention authentication or permission requirements.

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 efficient sentences with zero filler. Delivers purpose, consent requirement, side effects, and idempotency in a clear front-loaded structure.

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 exists, but description adequately explains return effects (welcome email, CRM record). Covers behavioral aspects and consent requirement, making the tool self-contained for an agent.

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% with built-in descriptions for all three parameters. Description adds minimal extra meaning beyond repeating 'optional' for city and name. Baseline 3 is appropriate as schema already documents parameters 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?

Clearly states verb 'Signs a user up' and specific resource 'SOMA's pre-launch waitlist (the Founding Fifty)'. Differentiates from sibling tools that are about beer products, brands, and billing.

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 'Only call this with the user's explicit consent' and describes the effects (stores contact, sends welcome email). Does not explicitly mention when not to use, but the consent condition implies strict usage 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?

No annotations are provided, but the description thoroughly lists the data fields returned. However, it lacks explicit behavioral traits such as read-only nature or any ordering, which would add transparency.

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, efficient sentence that packs in all relevant details without wordiness. It is front-loaded with purpose and enumeration.

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 provides a comprehensive list of returned data fields, covering style, profile, ABV, pricing, etc. It is complete for a no-parameter list 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?

With zero parameters, the baseline is 4. The description adds no parameter information, but there are no parameters to describe, so this score 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 it lists the 'full product lineup' and enumerates specific attributes (style, tasting profile, ABV, etc.). It distinguishes from siblings like get_beer by emphasizing it's the complete lineup.

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 use for a broad overview rather than individual beer details, but does not explicitly state when to use versus alternatives or include any when-not guidance.

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