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

Annotations already declare destructiveHint=true, but the description goes well beyond them by disclosing exactly what is destroyed versus restored, the guard that refuses deletion while elements reference the section, and the preview-vs-apply gating. That is precisely the extra context an agent needs before triggering an irreversible mutation.

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 compact sentences plus a short default clause; the reversal behavior is front-loaded and the parenthetical guard is placed inline where it matters. No filler or restated title.

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 destructive mutation with no output schema, the description covers purpose, default target selection, safety guard, and preview/apply behavior. The phrase 'then reads back' gestures at the return value but does not say what is returned, which is the only meaningful gap given no output schema exists.

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 50% – only runId is documented in the schema, and apply has no description there. The description compensates by defining apply's semantics (previews unless true) and restating the runId default, adding real meaning rather than repeating an uninformative boolean default. It stops short of describing runId's format or where ledger run ids come from.

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?

States a specific verb (reverses/undoes) and a specific resource (a section_write run from the ledger), then enumerates the two possible reversal semantics (delete created section vs. write back replaced section). This clearly distinguishes it from section_write and from unrelated *_undo siblings such as cs454_moving_loads_undo or skew_grillage_undo.

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?

Gives clear operative context: it targets the latest section_write run not yet undone, and it previews unless apply: true. The paired relationship with section_write is implied by the naming, and the refusal condition while elements use the section tells the agent when it will fail, but there is no explicit sentence routing the agent back to section_write or section_read for alternatives.

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