undo_list

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

Annotations only supply readOnlyHint=true, but the description goes well beyond: it explains that truncated is measured rather than guessed and prescribes re-running with a higher limit, and it defines the effectVerified field as distinguishing PROBABLE from confirmed reversals with an explicit caveat against over-reporting. That is substantive behavioral disclosure.

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?

Front-loaded with the purpose and the undo_apply handoff, then the truncated and effectVerified semantics. The 'measured, not guessed from a length coincidence' aside is slightly wordy but still earns its place by justifying the flag's reliability.

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, the description nonetheless describes the return shape (original tool, inverse tool, human note, truncated, effectVerified) and covers both parameters plus the safety caveat for unverified effects. Nothing an agent needs to call or interpret this tool is missing.

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%, so the description carries the full burden and does: limit is documented as max rows with default 50, and target is explained as unused/host-local and accepted only for CLI uniformity — a genuinely valuable disclosure no schema field provides.

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 and resource ('List recorded, not-yet-applied undo tokens'), adds ordering ('most recent first'), and distinguishes the tool from its sibling undo_apply by framing this as the reader and that as the applier. An agent can identify it without opening the 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?

Explicitly routes the agent: 'Use the undoId with undo_apply', and adds a conditional rule — when effectVerified is false, check live state before applying. Clear operating context, though it gives no explicit when-not-to-use or alternative for listing vs any other discovery mechanism.

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