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

With no annotations, the description carries the full burden of behavioral disclosure, but it falsely claims 'read-only', 'no side effects', and 'idempotent' for a tool that cancels a subscription. This is actively misleading and sets false expectations about side effects, authentication, and rate limits.

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 long and repetitive, with a 'Behavior' section and a 'Behavioral Transparency' section duplicating the same false claims. Much of the content is irrelevant to cancellation and should be removed.

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 mutating tool with no output schema and no annotations, the description must explain actual side effects, errors, and results. It instead claims there are no side effects and gives generic analysis-tool boilerplate, leaving an agent completely unprepared for the real behavior of canceling a subscription.

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 Args section provides useful semantics for subscription_id, at_period_end, and prorate that go beyond the raw schema. However, api_key is left undocumented, and the surrounding false behavioral claims undermine trust in the parameter descriptions.

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 opening phrase 'Cancel a Stripe subscription' is clear, but the Behavior section immediately claims the tool is read-only and produces analysis output, directly contradicting the stated purpose. An agent cannot reliably determine whether this cancels a subscription or performs analysis.

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 'When to use' section recommends using this tool for structured analysis or classification, which is irrelevant and misleading for a subscription cancellation tool. No guidance is given on when to cancel versus using sibling tools like create_subscription or list_invoices.

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 claims 'without modifying external systems' and 'No side effects', which is false for a tool that creates a Stripe Checkout session. It also says 'No authentication required for basic usage' despite an api_key parameter in the schema. These are serious misrepresentations that would lead to incorrect invocation.

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

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

The description contains a relevant opening and Args section, but the Behavior and When-to-use sections are bloated with irrelevant and contradictory content that adds no value. It is not concise and the structure wastes space on misinformation.

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?

The tool has 6 parameters, no output schema, and no annotations, so the description must carry full contextual weight. It fails to explain authentication, the real side effects, what exactly is returned, or how api_key is used. Instead it provides false assertions about determinism and side effects, making the description incomplete in a way that is actively dangerous.

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

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

The description provides meaningful explanations for five of six parameters (price_id, success_url, cancel_url, mode, customer_email) in the Args section. However, it completely omits api_key, which is present in the schema. With 0% schema coverage, the description partially compensates but leaves a critical parameter unexplained.

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 opening sentence 'Generate a Stripe Checkout URL for a price' is a clear verb+resource statement. It doesn't explicitly differentiate from siblings like create_subscription, but the resource is distinct enough. However, the later 'When to use' section introduces unrelated structured-analysis language that muddies the purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'When to use' section says to use this tool for 'structured analysis or classification of inputs against established frameworks' — completely unrelated to creating a Stripe Checkout session. This is actively misleading guidance that would send an agent down the wrong path. No alternative tools are mentioned.

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 claims 'No side effects' and 'without modifying external systems,' yet creating a Stripe customer inherently modifies an external system via the Stripe API. It also claims 'No authentication required for basic usage' while the schema includes an api_key parameter. The description contradicts the tool's fundamental nature as a side-effecting, authenticated external API call.

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 organized into labeled sections, which is structurally sound, but large portions are filled with irrelevant content about analysis/classification that belongs to a different tool. These misleading blocks should be removed entirely; the useful content is only the first line and parameter list.

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 mutation tool hitting an external service, the description should disclose auth requirements (api_key), side effects, rate limits, and return behavior. It instead claims the opposite of the truth — no side effects and no auth. It also fails to describe what the created customer returns. The definition is seriously inadequate and misleading for the actual operation.

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 0%, so the description must document parameters. It covers name, email, and metadata with reasonable examples, but omits the api_key parameter entirely even though it is present in the schema and relevant to the tool's true behavior. This leaves the agent uninformed about one of the four parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The opening line 'Create a new Stripe customer' states a clear verb+resource, but the Behavior section immediately contradicts it by claiming the tool 'generates structured output without modifying external systems' and frames it as a 'structured analysis or classification' tool. An agent reading the full description would be confused about whether this creates a customer or performs analysis.

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 'When to use' section suggests this tool is for 'structured analysis or classification of inputs against established frameworks' — completely unrelated to creating a Stripe customer. The 'When NOT to use' warning about production decision-making is also irrelevant to a customer-creation operation. This guidance actively misleads rather than helps.

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 responsibility for behavioral disclosure. It claims the tool is 'read-only', 'produces no side effects', and 'does not modify any external state, databases, or files.' For a tool named create_subscription with Stripe customer/price IDs, this is highly misleading and likely false. The detailed behavioral bullets are transparent in form but inaccurate in substance.

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 long and highly repetitive: 'no side effects', 'read-only', and 'no authentication' appear multiple times. The boilerplate 'Behavioral Transparency' section duplicates earlier claims and adds irrelevant content for a subscription tool. The verbosity obscures rather than clarifies the tool's actual purpose.

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 and no annotations, the description should clarify the real effect, return value, and side effects. Instead it describes a fictional in-memory analysis tool and omits what happens when a subscription is created. It is incomplete and misleading for the actual Stripe operation implied by the tool name and inputs.

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 Args section adds useful meaning for customer_id, price_id, and trial_days, including ID format hints. However, schema coverage is 0% and the api_key parameter is completely omitted. The later auth note refers to MEOK_API_KEY environment variable, not the api_key parameter, leaving one parameter undocumented and creating confusion.

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 opening line 'Subscribe a customer to a price/plan' states a clear verb and resource, but the next lines claim 'This tool generates structured output without modifying external systems' and describe it as 'structured analysis or classification.' This directly contradicts the tool's name, Stripe parameters, and sibling tools. An agent cannot determine whether this creates a subscription or performs read-only analysis.

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 'When to use' section says to use it for 'structured analysis or classification,' which does not match a subscription-creation tool. The 'When NOT to use' warning about 'real-time production decision-making' is unrelated and provides no guidance on when to choose create_subscription over siblings like create_checkout_session or cancel_subscription.

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 the full burden, and it does disclose side effects, idempotency, rate limits, auth, error handling, and data privacy. However, some claims are internally inconsistent with the tool's stated function: 'All processing happens locally within the MCP server process' and 'No input data is... transmitted to external services' sit oddly beside a Stripe balance lookup, and the auth model is muddled (no auth vs. MEOK_API_KEY vs. api_key param). This keeps it from being fully trustworthy.

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 long and repetitive: the 'Behavior' section and the 'Behavioral Transparency' bullet list cover the same points (read-only, auth, rate limits, idempotency). The boilerplate 'When to use' section adds noise without value, so not every sentence 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?

The description gives useful operational details (returned balances/payouts, rate limits, error shape), but it omits the meaning of the api_key parameter and contains an irrelevant usage section. Without an output schema, the return description is thin (no structure for the 'error' objects beyond a key name), leaving the agent under-informed 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 schema has one parameter (api_key) with no description, and schema coverage is 0%, so the description must explain it. It only mentions MEOK_API_KEY environment variable for Pro tiers and never clarifies whether/how the api_key argument should be populated; this is confusing and insufficient.

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 opening sentence states a specific verb and resource ('Get current Stripe account balance and recent payouts') and the second sentence defines the return content, so the core purpose is clear. However, the later 'When to use' text describes 'structured analysis or classification of inputs against established frameworks,' which is unrelated to balance retrieval, and no sibling differentiation is provided (e.g., vs. get_revenue_metrics).

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 'When to use' section is boilerplate that describes classification/analysis tasks, not retrieving balances, so it actively misroutes the agent. It never names or contrasts sibling tools such as get_revenue_metrics or list_invoices, and the 'When NOT to use' caveat about real-time production decisions is generic and not tied to the tool's actual capabilities.

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 covers it thoroughly: read-only, stateless, idempotent, no side effects, authentication requirements, tier-based rate limits, structured error handling, and data-privacy guarantees. This goes well beyond what annotations would typically provide.

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 repetitive: read-only/stateless behavior, rate limits, and authentication details appear multiple times across the 'Behavior' section and the 'Behavioral Transparency' bullets. The 'When to use' paragraph adds little and even describes a different kind of tool, so not every sentence 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?

Operationally, the description is strong: it explains side effects, auth, rate limits, error handling, and idempotency. However, there is no output schema, and the description never specifies the exact return shape or field types beyond naming the computed metrics, leaving a clear gap for an agent that needs to consume the result.

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

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

The schema documents only an optional api_key parameter with a default, and schema description coverage is 0%. The description mentions that no auth is required for basic usage and that Pro tiers use a MEOK_API_KEY environment variable, but it never explains how the api_key parameter itself is used or what values it accepts.

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 opening sentence states a specific verb and resource: 'Calculate MRR, ARR, churn rate, and LTV from live Stripe data,' and enumerates the metrics. This distinguishes it from sibling tools that create, cancel, or list Stripe objects, though it does not explicitly name or contrast those 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 includes both 'When to use' and 'When NOT to use' sections, and the main body clearly implies use when revenue metrics are needed. However, the 'When to use' text is generic and poorly matched—'classification of inputs against established frameworks or standards' is not what this tool does—and no alternative sibling tools are named for comparison.

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 comprehensively discloses side effects (read-only, no external modification), authentication requirements, rate limits, error handling, idempotency, and data privacy. This is thorough, explicit behavioral disclosure beyond what structured data provides.

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 well-structured with clear headings and front-loaded summary, but it is repetitive: the 'Behavior' and 'Behavioral Transparency' sections restate side effects, authentication, and rate limits. The 'When to use' section is generic filler that adds noise rather than value.

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 list tool with no annotations and no output schema, the description covers the essential operational context: safety profile, auth, rate limits, error behavior, idempotency, and determinism. The main gaps are the undocumented response shape/pagination and the ambiguous api_key parameter, but the tool remains safely invokable for basic usage.

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

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

Schema description coverage is 0%, and the description compensates well for customer_id (prefix and meaning), limit (default 10, max 100), and status (allowed values). However, the schema's api_key parameter is not explained as an argument; the auth section references an environment variable instead, leaving ambiguity about how to pass an API key through the tool call.

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 opens with a specific verb and resource: 'List recent invoices for a customer.' It further clarifies the customer_id as a Stripe customer ID (cus_...), and no sibling tool performs invoice listing, so it is clearly distinguishable from tools like create_customer or search_customers.

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?

Although 'When to use' and 'When NOT to use' sections exist, the content is generic boilerplate about 'structured analysis or classification of inputs against established frameworks or standards' that is unrelated to listing invoices. It does not state when to prefer this tool over siblings or provide actionable selection criteria, and the guidance is actively misleading.

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 are absent, so the description must fully disclose behavior. It claims read-only and idempotent, but the description includes contradictory statements: it says 'No authentication required' but later mentions API key for Pro/Enterprise tiers. Also, it says 'read-only and produces no side effects' which is consistent, but the description's generic 'When to use' text about 'analysis or classification' is misleading. The rate limits and privacy details add value, but the inconsistency lowers the score.

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 overly verbose with redundant sections. It repeats 'read-only', 'no side effects', and 'idempotent' multiple times (in the opening, in Behavioral Transparency, and in other sections). The 'When to use' section is generic and irrelevant, adding noise. The front-loading is good with the clear first line, but the length and repetition undermine conciseness.

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

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

Given the tool has no output schema, the description must explain return format; it mentions error objects but not successful response structure. The description covers safety, rate limits, and idempotency, but the instability with auth requirements and the generic usage guidelines leave gaps. The tool's purpose of searching customers is simple, but the description's extraneous content and contradictions limit completeness.

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 schema has 0% description coverage for parameters, and the description introduces a third parameter 'api_key' not shown in the schema's properties (actually it is in the schema but not documented in the description). The description explains 'query' and 'limit' in Args, but does not explain 'api_key', and the schema itself lacks descriptions. The description provides some details for query and limit, but fails to cover all parameters, leaving the agent to guess about api_key.

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 searches Stripe customers by email or name, which is a specific verb and resource. However, it does not explicitly differentiate from sibling tools like list_invoices, but the purpose is clear enough for an agent to understand its role.

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 includes a 'When to use' section that is generic and mentions 'structured analysis or classification', which seems unrelated to searching customers. There is no explicit mention of alternatives among siblings, and the 'When NOT to use' is vague and not directly about customer search.

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