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

Annotations already flag destructiveHint=true and idempotentHint=false, but the description adds a crucial behavior not in the annotations: writes preview first and change nothing until re-invoked with confirm: true. It also discloses the rejection behavior for read operations and the pass-through argument convention. This two-phase commit semantics is exactly what an agent needs before invoking a destructive tool.

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 short sentences, front-loaded with the core purpose before the preview/confirm protocol and then the sibling exclusion. Every sentence carries information, though the closing "Call it only when there is a change to make" partially restates the opening write-operation framing.

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?

With no output schema and only two schema-documented parameters, the description covers what matters for correct invocation: which operation kind is accepted, how arguments are nested, and the preview/confirm lifecycle. It stops short of describing what the preview response looks like or how rejection errors surface, which would help an agent recover from mistakes.

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 both schema fields already say tool is "the write operation name, from discover" and arguments take the operation's own args including confirm: true. The description reinforces the delegation pattern ("Always pass tool ... and put the operation's own arguments inside arguments") but adds no syntax, format, or constraint detail beyond what the schema states, so the baseline of 3 applies.

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 opens with a specific verb and scope: "Run a write operation (kind write in discover) such as an update, create, delete or status change." It explicitly contrasts with the sibling read path ("Rejects read operations; use query for those"), so an agent can distinguish execute from query and discover without inspecting any schema.

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 explicit when-to-use ("only when there is a change to make"), when-not-to-use ("Rejects read operations; use query for those"), and names the discovery prerequisite ("from discover"). The alternative tool is named together with the condition that selects it, leaving nothing to inference.

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