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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is structured. The description adds genuine context by bounding the destruction (cancels inquiry arrangements, not contracts or tenancies) and naming the alternative channel. It stops short of saying whether withdrawal is reversible, what state the application ends in, or how the destructive action interacts with the confirmed flag.

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 with no filler and the action front-loaded, which is good. But the prose is weighed down by internal jargon ("the owning inquiry," "owns the journey") that obscures more than it conveys, so the compactness comes partly at the cost of clarity.

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?

An output schema exists, so return values need not be described, and the destructive scope is covered. The gap is operational: a five-parameter destructive mutation with a version guard and idempotency key is called without any explanation of versioning, retry semantics, or what the confirmation flag enforces. An agent could invoke it and hit version conflicts or mis-set confirmed without warning.

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 0% across five parameters, and the description says nothing about any of them. The concurrency token (expectedVersion, a date-time), idempotencyKey, sessionToken and the const-constrained confirmed flag are completely undocumented; the schema gives only types and a maxLength. With zero coverage the description was required to compensate and does not.

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 gestures at the action ("Record the customer's explicit loss of interest... and cancel its arrangements") rather than plainly stating "withdraw this application." The phrase "owning inquiry" and the title's "viewing inquiry" blur the line against the sibling viewings.cancel, which is the exact distinction an agent most needs. It does carve out an explicit negative scope ("cannot cancel a contract or tenancy").

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 gives one concrete exclusion: once a Request owns the journey, contact the team instead. That is real routing guidance, but it names no sibling tool (viewings.cancel, viewings.decline_proposals, applications.update) and states no precondition for the normal case. Usage is implied rather than spelled out.

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