AdCreator AI Ad Headline Generator

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

Description independently confirms the read-only nature ('Read-only and free, no signup'), consistent with annotations. It adds useful behavioral guidance on failure ('If the call fails, report that — do not invent headlines') and describes the output labelling, which goes beyond 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?

Four sentences front-load the core purpose, then cover inputs, output, and failure handling. There is minor redundancy ('free' appears twice) and the image/video-ad pointer is extra, but the description remains compact 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?

No output schema exists, yet the description explains what will be returned: 10 headlines, each labelled with persuasion technique, plus a conversion-tip reference. Required and optional inputs are stated, and the failure handling is explicitly covered. For a simple 3-parameter tool, this is complete.

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

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

Schema coverage is 100%, with examples and enum for platform, so the schema already carries the parameter details. The description mostly restates that product should be name + short description and that audience/platform are optional, adding only marginal semantic value.

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 ('Generate'), exact output count ('10'), and target resource ('ad headlines for an e-commerce / Shopify product'). The conversion-focused and platform context make the tool's purpose unmistakable, even with no siblings to distinguish.

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 tells the agent what to provide ('Provide the product...') and that audience and platform are optional. It does not name alternative tools, but there are no siblings, so the context is clear enough. Could be slightly stronger with an explicit 'use when...' statement.

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 and idempotentHint. The description adds meaningful behavior beyond that: it requires a specific Authorization Bearer adcmcp_… header, explains that an unconnected merchant will receive connection instructions, and reaffirms the operation is read-only. 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 and front-loaded with the core purpose, then covers the auth prerequisite and fallback behavior in a few tight sentences. Every sentence adds useful information 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 zero-parameter, read-only usage query, the description is nearly complete: it states the inputs it needs (connection token), the outputs it provides (creatives used, limits, remaining, all-time), and behavior when not connected. It does not specify the exact response format, but no output schema exists and the described data points are sufficient for tool selection.

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 and the schema coverage is 100%, so there is no parameter ambiguity for the description to resolve. The auth token mentioned in the description is a server configuration requirement, not an input parameter, and it is clearly described.

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 and resource: it reports AdCreator usage for a connected Shopify merchant. It enumerates exactly what is returned — monthly ad creatives and videos, plan limits, what is left, and all-time creatives — which makes the tool's purpose unambiguous and distinguishable from the 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 clearly states the intended context: a connected AdCreator merchant wanting usage information. It also gives the key prerequisite, the AdCreator connection token, and notes what happens when not connected. It does not explicitly compare against the sibling get_my_plan tool, but the context is clear enough for correct selection.

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

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

Beyond the readOnly/idempotent/destructive annotations, the description discloses the auth prerequisite (AdCreator connection token) and the conditional behavior when not connected (explains how to connect). This adds meaningful behavioral context with 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 tight sentences with no filler. The target audience and main deliverable are front-loaded, and the auth requirement and fallback behavior are covered economically.

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 no-parameter, read-only information tool without an output schema, the description says what is returned, under what precondition, and what happens when that precondition fails. Nothing essential 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 takes zero parameters, so there is no parameter-semantics burden on the description. The schema is empty and the description aligns with that by not implying any inputs.

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 outcome: it reports the merchant's current plan, price, and the exact additions and pricing of each higher plan. This clearly distinguishes it from siblings like generate_ad_headlines and get_my_ad_usage.

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?

Provides clear context by specifying it is for a connected AdCreator merchant and notes the connection-token requirement. It does not explicitly name alternatives or exclusions, but the scope is clear enough that an agent can infer when to use it.

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