delete_verdict

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

With no annotations, the description carries the full behavioral burden and does substantial work: it discloses the refusal case (human APPROVED seals), a state gate on already-reviewed shapes reusing edit_shape's rule, and the mutation semantics ("Journaled like every mutation, so undo_last re-seats a lifted mark exactly where it was"). The disclosure of reversibility and failure modes is strong; the "the same line edit_shape holds on reviewed shapes" clause is allusive jargon that an agent may not decode without reading edit_shape.

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 dense sentences, front-loaded with the action and the id source before the constraints. The middle clause about edit_shape and reviewed shapes is compressed to the point of ambiguity and could be unpacked or dropped; otherwise there is 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 one-parameter mutation with an output schema, the definition covers what an agent must know before calling: the id's provenance, the refusal condition, and recoverability via undo_last. The remaining gap is the opaque reviewed-shape rule, which leaves an agent guessing at the exact error condition rather than the outcome.

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 the single parameter's description already states "Record id from mark_verdict or list_annotations verdicts[]", which the prose merely restates in almost identical wording. No format, example, or validation detail (e.g. what an invalid id looks like) is added beyond the schema, so the baseline 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?

"Lift an agent verdict mark by id" names both the verb (lift/remove) and the exact resource, then scopes it to agent verdicts as distinct from human seals. It also points at the two sibling sources that produce the id (mark_verdict and list_annotations verdicts[]), so an agent can distinguish it from delete_shape or delete_rfi without opening a 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?

The description gives an explicit when-not condition: "Agent marks only: the estimator's APPROVED seal is human ink and is refused," which prevents a wasted call on the wrong mark type. It also tells the agent where the id comes from. It stops short of naming what to do instead when a human seal must be removed, so it is clear context rather than full when/where/alternatives routing.

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