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

The description contributes a lot that annotations do not: what is destroyed (source + its transactions), what is preserved (vendors, aliases, subscriptions — "the person's words"), what is side-effected (receipts unmatch and are listed), and what is freed (the hash). However, "source and its transactions deleted" directly conflicts with destructiveHint=false, and an agent reading the annotation alone would be misled about the operation's weight.

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 action and its consequence, and mostly dense. The closing "Effects:" line restates material already given ("the hash is free again afterwards" / "hash free to import again"), and shorthand like "(P-2)" and "Owner's act" carries little meaning for an outside agent.

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 2-parameter mutation tool with no output schema, the description covers the important unknowns: reversibility, what survives, and the re-import path. It stops short of stating the permission/authority check implied by "Owner's act" or what the listed unmatched receipts look like in the response.

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 both parameters are already documented with examples ("SRC-0001", "a misread column, the wrong file, a re-read"). The description adds only the framing that the reason is recorded ("on the record"), which is marginal above 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?

The first sentence names a specific verb and resource ("throw out one imported statement and every row that came from it, with a reason") plus the intent behind it ("so it can be re-read and imported again"). That is enough to separate it from purch_import_statement, purch_get_transaction and pros_discard_pull without opening any 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 P-2 policy sentence gives the agent the decision rule: a wrong row means a wrong source, so rows are never edited; the statement is discarded and re-imported from a fresh read. It never names an explicit alternative tool or a "do not use this when" exclusion, which is why it falls short of a 5.

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