Ontrack Moving Quotes

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real context: output is status-only with no personal details, and receipt tokens must never be placed in URLs, which is a security constraint an agent would otherwise miss. It does not describe error behavior for invalid or mismatched tokens.

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, front-loaded with the action and result scope, followed by the security caveat. Every sentence carries information, though the clipped phrasing leaves some ambiguity about what 'status' values exist.

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 two-parameter read-only lookup with no output schema, the definition covers the essentials: what is returned and a key security constraint. It is still thin on token lifetime, behavior on invalid tokens, and the relation between the two required parameters.

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?

Both parameters are required and schema description coverage is 0%, so the description must compensate. It establishes that receipt_token is private credential material and must not leak into URLs, but it does not explain the roles of request_id versus receipt_token or that they must correspond to the same request; the hex patterns live only 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 states a specific verb and resource: check a quote request's status using its private receipt token. It also scopes the result ('status only, no personal details'), which helps an agent distinguish it from the sibling request_moving_quote, though it never names that sibling explicitly.

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 phrase 'Check this request using its private receipt' implies the flow: after submitting a quote request, use the receipt to poll status. There is no explicit when-not guidance, no statement about token expiry or reuse, and no reference to the creation sibling as the counterpart step.

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 annotations, the description discloses screening and sales routing behavior, receipt semantics, consent requirements, and the constraint not to quote prices or promise bookings. These details materially help the agent understand what the external write does and what guarantees it 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 front-loaded with the purpose and then proceeds through workflow, constraints, receipt semantics, routing, and prerequisites. Every sentence carries operational value, with no 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 complex external submission tool with consent and idempotency requirements, the description covers the critical context: prerequisites, permission handling, missing fields, receipt meaning, and status interpretation. It is complete enough to call correctly despite there being no output schema.

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 already 91%, and the schema documents idempotency, consent, contact fields, and empty-value handling. The description reinforces that unknown destination/date/size may be empty and that details must not be invented, but it adds little parameter semantics beyond the schema itself.

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 a specific verb and resource: submitting a moving quote request to Ontrack. It clearly distinguishes this submission action from the sibling status-retrieval tool by focusing on creating the request and interpreting the resulting status.

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 provides explicit workflow guidance: ask conversationally, show a summary, obtain permission before calling, and only call when an Ontrack connection is enabled. However, it does not explicitly name when to use get_quote_request_status or give exclusions beyond the permission and connection prerequisites.

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