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

The destructiveHint annotation already flags this as a write, but the description adds genuinely non-obvious behavioral context: 'WRITE: changes the accounting records' plus the idempotency warning 'Makes one request that is never repeated; check the result before trying again'. That retry/safety guidance is exactly what an agent needs for a non-idempotent mutation and is not derivable from the annotation.

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?

Four compact sentences, front-loaded with the WRITE prefix and the retry warning before the purpose statement. Every sentence carries information, though the ordering puts safety guidance ahead of what the tool actually does, which slightly slows comprehension.

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 100% schema coverage and an existing destructiveHint annotation, the remaining burdens are mode selection and mutation safety, both of which the description covers. No output schema exists, so the absence of return-value documentation is not a gap.

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 adds the mutual-exclusivity rule between the simple and collective parameter sets and the 'debit and credit sums must match' validation constraint, which is not encoded anywhere in the schema. It is a modest but real increment over the structured fields.

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 ('Creates a manual book entry in the journal') and even names the endpoint (POST /journal/create.json), which no sibling shares. An agent can immediately distinguish it from cashctrl_create_order and cashctrl_create_person.

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 lays out the two supported modes ('Either a simple entry (debit_account_id, credit_account_id, amount) or a collective entry (items, whose debit and credit sums must match)'), which is real selection guidance. It stops short of naming when-not or pointing at sibling alternatives (e.g. update/delete journal entries), so it does not reach 5.

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