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

Annotations already declare destructiveHint=true and readOnlyHint=false, so permanence is partly structured data; the description still reinforces it and adds genuinely new behavior: a mandatory human-confirmation step and an origin-based eligibility rule (manual only). It does not describe what happens on a repeat or mismatched call, leaving the idempotentHint unqualified.

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?

Three short sentences, each doing distinct work: what is deleted, the confirmation/ID protocol, and the exclusion. Destruction is front-loaded in the first sentence with zero 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 destructive, narrow-scope tool the essentials are present: eligibility, confirmation requirement, and ID source; an output schema covers return values. The only real gap is guidance on operation_id and on behavior when the ID is not a manual record.

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 must carry parameter meaning. It explains transaction_id (must be the ledger ID) and implies confirm (explicit user confirmation), but never mentions operation_id or its purpose as a replay-safe key, leaving one of three parameters undocumented anywhere.

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?

"Permanently remove one exact owned manually recorded BUY or SELL transaction" gives a specific verb, a single-record scope, and ownership/manual-origin qualifiers. The trailing restriction on imported or broker-synced records further narrows what this tool actually deletes, so an agent can distinguish it from edit_/record_ siblings 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?

It states the preconditions clearly (user must explicitly confirm, transaction ID must come from the ledger) and gives an explicit exclusion (never imported or broker-synced records). It does not name the edit_my_portfolio_transaction alternative for correction-instead-of-deletion cases, so routing guidance is strong but not complete.

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