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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description goes well beyond them by disclosing irreversibility ("no undo from here") and the side-effect boundary ("their past orders are kept"). That is exactly the context an agent needs before executing a destructive call.

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 short sentences, front-loaded with the action, then the input constraint, then the confirmation requirement, then the ambiguity fallback. No filler and no repetition of annotation data.

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 one-parameter destructive tool with full schema coverage and no output schema, everything an agent needs is present: ID provenance, mandatory human confirmation, irreversibility, retained-order behavior, and multi-match handling.

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 extra credit by repeating the ID-only constraint at the call site and pointing to the sibling that produces valid values, reducing hallucinated name-as-ID inputs. It stops short of adding format detail beyond what the schema says.

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?

Starts with a specific verb+resource ("Remove a customer from the merchant's list") that unambiguously separates it from hub_delete_product, hub_delete_media_file, and the other delete siblings. The agent needs no schema access to know what it does.

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 explicit preconditions and alternatives: resolve the ID via get_customers, never guess, confirm with the merchant naming the customer, and if multiple customers match, list them and ask rather than picking. It is effectively a decision procedure, not just a usage hint.

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