MCP CPG Human in the Loop (HITL)

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

With no annotations, the description discloses that the tool returns current status and an answer when available, and implies a polling behavior. It does not mention side effects, but the behavior is clear.

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, front-loaded with purpose, 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?

For a simple poll tool with one parameter and no output schema, the description sufficiently covers purpose, input expectation, and return value. It does not explain how to obtain the ticket_id from sibling tools, but that is implicit.

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 already describes the ticket_id parameter with format. The description adds no additional meaning 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 uses a specific verb ('Poll') and resource ('ticket previously lodged'), and lists the ticket types (RFQ, terms request, escalation), clearly distinguishing from sibling tools that create tickets.

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 after submitting a ticket via sibling tools, but does not explicitly state when not to use it or provide alternatives.

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 does well: it reveals the core side-effect (handoff to human review), names the emitted signal (CPG-451 ESCALATE), and states the return value (ticket ID). It does not mention irreversibility or downstream human-review behavior, but the main behavioral traits are 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?

Two tight sentences with no filler. The trigger condition is front-loaded, followed by the emitted code and the return behavior. Every phrase 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?

For a 5-parameter tool with no output schema and no annotations, the description gives enough to invoke correctly: when to use it, what happens, and how to follow up via check_rfq_status. It could add a bit more about what CPG-451 means or post-escalation expectations, but nothing essential is missing for initial use.

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 documents all five parameters well. The description adds no parameter-level meaning beyond the schema, which matches the baseline of 3.

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?

Uses a specific verb ('Hand to... human review') and names the exact resource (GSC Navigator, CPG-451 ESCALATE). Clearly distinguishes itself from siblings like submit_rfq or check_rfq_status by focusing on deterministic failures that require human intervention.

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?

States the activation condition explicitly: matters that cannot be resolved deterministically. It also points to check_rfq_status for polling the resulting ticket, but does not explicitly say when not to use request_terms or submit_rfq, so it lacks full exclusions.

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 burden of behavioral disclosure. It does so by revealing the asynchronous nature ('lodged as a ticket and a human answers it'), the output contract ('Returns a ticket ID'), and the polling pathway. It does not mention failure modes or persistence details, but the essential behavior is 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?

Three short sentences with no filler. The first sentence front-loads the tool's purpose, the second explains the mechanism, and the third states the return value and follow-up step. 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?

For a ticket-creation tool with five parameters and no output schema, the description provides the key operational context: human-mediated answering, asynchronous processing, and a ticket ID for polling. It is slightly thin on how it relates to escalate, but the schema covers parameter formats and the core workflow is clear.

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 context that the question parameter is what a human answers and that the response is a ticket ID, but it does not enrich individual parameter semantics 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?

Description opens with a specific verb ('Ask') and a clear resource ('commercial or procedural question'), then enumerates topic examples such as terms, conditions, eligibility, and process. It also distinguishes its output (a ticket ID for check_rfq_status) from the RFQ-focused sibling submit_rfq.

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 when to use this tool: when a human should answer a commercial or procedural question. It also tells the agent to poll via check_rfq_status afterward. It does not explicitly contrast with escalate or submit_rfq, so full when-not-to-use guidance is absent.

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 does well: it discloses that a human reviews every ticket, that no order is decided by this tool, and that it returns a ticket ID. It adds meaningful behavioral context beyond the bare act of submitting.

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?

Three focused sentences with no filler. It front-loads the core action, then adds the human-review behavior, the return-value workflow, and optional reference context in a natural order. 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?

Given there is no output schema, the description correctly states what is returned (a ticket ID) and what to do with it. Combined with 100% schema parameter coverage, the agent has enough to invoke the tool correctly and understand the follow-up step.

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's mention of GTIN and market code largely restates the schema's own parameter descriptions rather than adding new meaning. Required fields and their purposes are already fully documented in 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 uses a specific verb-resource pair ('Lodge a request-for-quotation with GreenCore Solutions Corp.') and clarifies this is a ticket submission, not an order-decision tool. It also distinguishes itself from the sibling check_rfq_status by stating it returns a ticket ID for polling.

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 places the tool in a workflow: submit the RFQ, then poll via check_rfq_status. However, it does not explicitly address when to use this tool versus request_terms or escalate, so only partial alternatives guidance is given.

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