AgencyAI Commerce MCP

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

Annotations already declare readOnlyHint=true, so the base safety is known. The description adds meaningful behavioral context: 'deterministic' (consistent output) and 'indicative' (not a definitive judgment), which go beyond the annotations. 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?

A single, well-structured sentence that front-loads the verb and resource. Every word earns its place, with no redundancy or 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?

For a straightforward tool with read-only annotations and a clear purpose, the description is sufficient for an agent to select and invoke it. The lack of output schema is not a major gap here, though the description could hint at the return format (e.g., a score or report).

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 each parameter. The description groups them as 'organization profile' but adds no additional meaning beyond what the schema provides, 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?

Description uses the specific verb 'Produce' with resource 'AI-readiness assessment' and clearly differentiates from sibling tools like book_consultation and get_service_offerings. The phrases 'deterministic' and 'indicative' add precision.

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 context via 'supplied organization profile' but does not explicitly state when to prefer this tool over alternatives or mention any exclusions. Sibling tools are distinct in purpose, but the description offers no direct 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?

The description adds valuable behavioral context beyond annotations: it's a legacy flow with no email/calendar side effects and no booking guarantee. This is important since annotations only indicate write semantics (readOnlyHint false). It doesn't contradict annotations, but it leaves out what happens on success (e.g., response or storage), so a 4 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 sentence that is immediately informative and front-loaded with the core action ('Submit a consultation request preview'). Every phrase earns its place, with no wasted words.

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 7 parameters and no output schema, the description is rather sparse. It clarifies what the tool does not do, but not what it actually does (e.g., whether it saves the request, returns an ID, or shows a preview). It's minimally viable but leaves gaps about the expected result and the meaning of 'preview'.

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 only 43%, which is low, so the description should compensate by explaining parameter meaning. It does not; it mentions no parameters at all. The schema itself has descriptions for only 3 of 7 params, leaving others ambiguous. Thus, the tool description adds no value in this dimension.

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 submits a 'consultation request preview,' which is a specific verb+resource action. It also distinguishes itself from siblings by clarifying it's a legacy flow that doesn't guarantee booking, making it clear this is not the main booking 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 when to use this tool (for preview submissions) by noting it doesn't send email, create calendar events, or guarantee a booking. However, it doesn't explicitly name alternatives or provide direct when-not-to-use guidance, so it falls 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 aligns with the readOnlyHint annotation by using the verb 'Read.' It adds the behavioral detail that results are filtered by a client profile and are from the 'current' catalog, but it does not disclose other traits such as authentication requirements or behavior when no parameters 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 a single, front-loaded sentence that immediately states the resource and action, 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?

For a simple read-only tool with three optional parameters and no output schema, the description adequately covers the main purpose. Some details like behavior with no parameters or exact return format are omitted, but the annotations mitigate the need for extensive disclosure.

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 already describes each parameter with 100% coverage. The description adds the collective term 'client profile' but does not provide additional detail beyond what the schema offers, so a 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 the verb 'Read' plus a specific resource ('AgencyAI's current AI operations service catalog') and the goal ('return packages matching a client profile'). This clearly distinguishes it from sibling tools like assess_ai_readiness and book_consultation, which serve different purposes.

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 retrieving service offerings based on a client profile, giving clear context for when to use the tool. However, it does not explicitly mention alternatives or when not to use it, so it lacks explicit exclusions.

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