MarginGlow AI Signal

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

The description discloses important behavior: it consumes one credit, returns structured evidence, and requires specific inputs. However, it directly contradicts the idempotentHint=true annotation: consuming a credit on every call is a side effect, so repeated identical calls would have additional effects. This is an annotation 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?

Four sentences with no filler: use case, requirements, return contents, credit cost, and exclusions. The most important information is front-loaded, and 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?

Combined with a full input schema, annotations, and an output schema, the description covers when to use, prerequisites, cost/side effect, return value, and boundary conditions. An agent has everything it needs to select and invoke the tool correctly.

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

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

Schema description coverage is 100%, so the schema already documents all four parameters. The description adds only that businessName and website are required, which duplicates the schema's required list. It does not materially clarify country or objective 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?

The description states precisely what the tool does: it produces practical, evidence-based growth opportunities for a specific small business, with concrete goals listed (revenue, margins, costs, Google visibility, conversion, prioritisation). It clearly separates this tool from the sibling credit-management tools by focusing on analysis output. No ambiguity remains.

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 explicit when-to-use guidance with user goals, explicit prerequisites (business name and public website), and explicit exclusions (generic definitions, investment/regulated advice, private financial data). This is strong enough for an agent to know when this tool is appropriate and when it is not.

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

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

Beyond the annotations, which already mark readOnlyHint and idempotentHint, the description adds a crucial domain-specific behavior: 'does not consume a Signal.' This is non-obvious and materially affects how an agent should treat the call, since signal consumption is likely a limited resource. It also discloses the response contents (balances, allowance, Stripe credit), giving full behavioral 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, front-loaded sentence that first states the action, then the key details, then the read-only caveat. There is no redundant wording or filler; every clause adds information.

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

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

For a zero-parameter, read-only access check with an output schema present, the description covers all necessary aspects: what it checks, what it doesn't do, and its safety profile. The output schema handles return-value details, so no further elaboration is required.

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 no parameter semantics to explain. The description adds meaningful context about what the access check reports, which is more than sufficient for a parameterless tool. The baseline of 4 for 0 parameters 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 uses a specific verb ('Checks') and clearly enumerates the resource and data points: complimentary and paid Signal balances, whether analysis can run, which allowance is used next, and the latest Stripe purchase. This makes the tool's function immediately distinguishable from its siblings, which analyze opportunities or purchase signals.

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 conveys clear context: it is a read-only status/pre-flight check that tells the agent whether analysis can run and which allowance will be used, strongly implying it should be called before analyse_small_business_opportunities or purchase_marginglow_signal. It does not explicitly name alternatives or state when not to use it, so it stops short of a 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?

The description discloses that the tool creates a payment link rather than directly granting access, includes cost and tax, and explains the automated versus manual checkout URL hand-off. It also describes the post-payment retry with the same API key and Idempotency-Key. The annotations already signal non-read, non-idempotent behavior, and the description adds practical flow details without 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?

Four sentences, each with a distinct purpose: the action, the trigger, the execution path, and the post-payment step. There is no redundancy and the core verb and price are 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 zero-parameter tool with annotations and sibling context, the description covers the trigger, cost, tax, checkout URL hand-off, automation capability, and what to do after payment. No output schema exists, but the description gives enough actionable information for an agent to invoke the tool 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 there are no parameter meanings for the description to add; baseline for zero-parameter tools is 4. The description usefully references the agent API key and Idempotency-Key as context for the retry flow, though these are not schema 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 description opens with a specific action and object: it creates a Stripe payment link for one MarginGlow AI Signal at EUR 2. This clearly distinguishes it from the sibling analysis and access-check 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 says to use this tool when analyse_small_business_opportunities reports no Signal credits remain, and it gives post-payment retry instructions. It does not explicitly state when not to use it, but the trigger condition implies that if credits remain, this purchase is not needed.

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