Discard workflow

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

Annotations cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), and the description adds real value beyond them: it discloses that no livestock/domain data is written, and it imposes an ownership/authorization requirement not visible anywhere in the schema. The "read-only scope but not a read" phrasing is awkward but consistent with readOnlyHint=false rather than contradicting it. It omits what state the preview is left in afterward.

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 short sentences, action front-loaded, no filler. Minor deduction for the telegraphic "without livestock writes" and the internally puzzling "Read-only scope but not a read," which cost a beat of parsing.

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 state-mutating tool with no output schema and half its parameters undocumented, the description covers the ownership prerequisite and the mutation boundary well. It does not say what happens to the preview after invalidation (retrievable? error on later use?) or confirm idempotent re-invocation behavior, leaving an agent to guess at the post-condition.

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 50% – preview_id, the single required parameter, has no schema description – and the description does not compensate, saying nothing about what preview_id identifies or what farm_id does. The only relevant hint is the owner constraint, which describes the actor rather than either parameter.

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?

"Invalidate an uncommitted preview" gives a specific verb plus resource, and the phrase "uncommitted preview" situates it in the preview→commit lifecycle alongside preview_workflow/commit_workflow. It never names those siblings, so differentiation is inferable rather than explicit.

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 prerequisite ("the requesting actor must be the preview owner") is stated, which is genuinely useful context for deciding whether the call will succeed. However, it never says when to discard versus when to commit or leave the preview alone, so the when-to-use decision is left implicit.

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