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

Annotations already declare the write/safety profile (readOnly=false, idempotent=false, destructive=false), so the bar is lower; the description adds real context by stating the terminal effect ('account added to the register') and by disclosing the auto-creation overlap with statement import. It doesn't say what happens on a duplicate name, which is the one behavioral gap for a non-idempotent add.

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?

The purpose and kind list are front-loaded, and the import/record_value routing follows in a single dense sentence. Some clauses (the house/car parenthetical repeated twice) are mildly redundant, but no sentence is 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 7-parameter mutation with no output schema, the description covers purpose, naming, the import overlap, and the asset-value follow-up. It leaves duplicate-name behavior unstated, which is the main thing an agent would still need to infer.

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; the description earns above that by explaining the rationale behind the `name` convention ('so statements find it'), which tells the agent why matching statement text matters, not just the format. The kind enumeration also maps onto the enum in plain language.

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?

Opens with a specific verb+resource ('Add an account to the register') and immediately enumerates the account kinds covered, so an agent can distinguish it from purch_update_account, purch_import_statement, and crm_add_account. The scope statement is concrete enough to route on 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 states the alternative path: importing a statement auto-creates a missing account, so hand-adding is only needed for a card/loan before its first statement or for a non-statement asset. It also names the follow-on tool (purch_record_value) and the condition that selects it.

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