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

Annotations declare destructiveHint=true, but the description carries far more: products are re-pointed to the replacement group or left completely untaxed if the parameter is omitted, tax rates survive deletion, there is no undo, and past sales are not recalculated. These are distinct behavioral traits (cascading side effects, irreversibility, non-retroactivity) that annotations alone cannot convey.

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 action and the highest-stakes consequence (products move / may go untaxed), then the rate-preservation clarification, then the confirmation requirement. Every sentence carries operational weight. The all-caps emphasis is heavier than necessary for an otherwise disciplined structure, which costs it the top mark.

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?

No output schema exists, and none is needed — the description covers cascading effects, the safe default choice, the confirmation step, irreversibility, and the temporal scope of the change. Nothing an agent needs in order to call this safely is missing.

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 the baseline is 3. The description goes beyond the schema text by attaching the business consequence to each parameter value — omitting replacementTaxGroupId means 'those products are sold UNTAXED from that moment' — which maps the parameter choice to an outcome rather than just a type.

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 ('Delete a tax group') and immediately distinguishes it from sibling operations by explaining what is preserved rather than deleted: 'The rates inside it are NOT deleted... use delete_tax_rate if the merchant really wants a rate gone.' An agent can route between hub_delete_tax_group, hub_delete_tax_rate, and hub_update_tax_group without opening any 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?

Explicit when-to-use and when-not guidance, plus routing to the correct alternative ('use delete_tax_rate'). It also prescribes the agent's workflow — 'Always ask the merchant which of the two they want' and 'CONFIRM WITH THE MERCHANT BEFORE CALLING, naming the group and how many products it affects' — which is exactly the missing guidance most destructive tools omit.

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