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

Annotations already flag readOnly=false, destructive=true and idempotent=false, and the description adds genuinely new context on top: what actually changes (the member's amount owing / account credit in the club's books), the emailing side effect of notify_by_email, and the concrete consequence of non-idempotency ('calling twice creates two transactions'). It also surfaces the human-confirmation requirement, which no annotation conveys.

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 operation verb and scope in the first clause, and each subsequent sentence adds distinct information (side effect, email, idempotency, confirmation, endpoint). The trailing 'POST /transaction.' is the only near-redundant element, but the rest is dense and waste-free.

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, non-idempotent write tool with no output schema and 8 parameters, the description covers the mutation's effects, the confirmation gate and non-idempotency, which is what an agent most needs. It stops short of telling the agent what is returned (e.g. whether a transaction ID comes back) so the agent can chain into get_transaction, which is the only notable 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 description coverage is 100%, including the is_credit, type, amount and notify_by_email definitions, so the schema already carries parameter meaning. The description restates is_credit's charge/credit duality and notify_by_email's email behavior but adds no new syntax, constraints or formats beyond what the schema documents - 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?

States a specific verb and resource ('create a financial transaction for a member') and immediately clarifies the two concrete variants: a charge, or a credit when is_credit is true, with examples (invoice line, manual adjustment). The 'WRITE:' prefix and the nature of the operation distinguish it cleanly from read siblings like hello_club_list_transactions and hello_club_get_transaction.

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?

Gives a clear precondition ('Confirm member, amount and type with the user first') and the context in which the tool applies (posting charges or credits to a member's account). It implies rather than states the split from read siblings - it never explicitly names list/get_transaction as the read-only alternatives - so it stops 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.