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

Annotations already declare destructive=true/readOnly=false, but the description adds substantial context beyond them: reversibility from Ledger, full audit trail, the conflict failure mode when already retracted, and a possible `needs_confirmation` envelope. Reversibility does not contradict destructiveHint — it refines it.

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 and largely earn-its-place, with the core remedy statement first and exclusions after. A couple of clauses (the quoted 'that's not right' reassurance, the 'THE remedy' emphasis) are slightly redundant with earlier sentences, adding density without new information.

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 mutation tool with no output schema, the description covers what an agent needs: the confirmation envelope it may receive, the conflict behavior, and the safety/reversibility profile. Nothing essential for correct invocation 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 coverage is 100%, so the baseline is 3, but the description adds real value by stating where entryId comes from ('Ids come from ledger_entries_list') and by tying `needs_confirmation` to the approvalId flow. It stops short of describing the workspace parameter's semantics, which the schema already covers.

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 ('Takes an entry out of the curated ledger') and immediately frames the purpose in operationally meaningful terms (correcting a mistaken record). It distinguishes itself from siblings like ledger_entries_settle and ledger_entries_update by scoping to retroactive removal of a wrongly recorded entry.

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?

Explicit when-to-use ('THE remedy when you recorded something wrong — a decision that wasn't made, a duplicate, a fact the user corrects') with concrete triggers, plus an explicit when-NOT-to-use ('Not for overturning a settled claim the team once believed — a human supersedes that'). The alternative and the condition selecting it are named.

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