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

The annotations already mark this as destructive and not read-only, but the description adds important consequences: 'This cannot be undone, and past supports lose the link to it.' It also gives the exception condition and the non-destructive alternative, going well beyond the structured hints.

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?

The description is three compact sentences and is front-loaded with the core action. Each sentence adds a distinct constraint or consequence: removal, exception, irreversibility, and alternative.

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?

An output schema exists, so return values need not be explained, and the annotations cover the destructive/idempotent profile. The description covers the operation's key behavioral constraints well, though it leaves the single required parameter 'id' unexplained.

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?

The schema has only one parameter, 'id', with 0% description coverage. The description never explains that the required integer is the UPI ID's identifier or what value should be supplied, leaving the parameter meaning to inference from the tool name alone.

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?

The description uses a specific verb and resource: 'Remove a UPI ID from the account.' It also distinguishes the action from the safer alternative by stating that 'switching it off instead keeps it,' which helps separate removal from update or deactivation siblings.

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?

It explicitly states when removal is not allowed: 'The last one, and the only active one, cannot be removed.' It also gives the alternative behavior: 'switching it off instead keeps it,' so an agent can choose between permanent removal and deactivation.

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