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

Annotations only supply destructiveHint=true, so the description carries most of the burden. It adds genuinely useful context: this WRITES a durable, filing-relevant compliance record rather than a transient one, and it names the source of the required input. It doesn't discuss idempotency/retry behavior or auth requirements, leaving that gap.

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, front-loaded sentences: what it does, then the required input provenance, then the endpoint. Nothing is repeated or padded, and the emphasis on WRITES/RECORDS is placed where an agent will read it first.

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 4-parameter write tool with a nested object and no output schema, the description covers purpose, the prerequisite call, and the compliance significance. The one real gap is that it doesn't indicate what the call returns (e.g. a transaction id needed by numeral_get_transaction), which matters more given there is no output schema.

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%, so all four parameters (including the nested metadata object and the SECONDS timestamp) are already documented in the schema. The description restates calculation_id and reference_order_id but adds no syntax or format detail beyond them, which is the baseline for a fully covered schema.

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 ('RECORDS a completed sale as a transaction') and immediately characterizes the artifact as a live tax/compliance record, which distinguishes it from read-only siblings like numeral_get_transaction. Naming the underlying call (POST /tax/transactions) and its dependency on numeral_calculate_tax further separates it from numeral_calculate_tax and numeral_create_refund.

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 establishes the ordering dependency: the agent must first call numeral_calculate_tax and pass its calculation_id. It gives clear context for when this tool is appropriate (after a completed sale). It stops short of naming a when-not case or pointing to numeral_create_refund as the alternative for reversals, so it isn't a full 5.

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