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

Annotations already declare destructiveHint and idempotentHint, but the description adds value beyond them: that the balance is destroyed along with the bundle, that no other tool can reverse it, the required billing write scope, and the self-registration 403 gate.

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-loads the destructive action and its consequence, then prerequisites. Four short sentences with little waste, though the repeated 'Needs a claimed...' framing is slightly redundant.

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 single-parameter destructive tool with no output schema, everything an agent needs — irreversibility, prerequisite read, auth scope, workspace claim gate — is present.

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% and the schema already explains credit_id as the id shown by list_credits; the description only repeats 'pass credit_id' without adding format or sourcing detail beyond the 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 ('Delete a credit bundle') plus material scope — the remaining balance goes with it — so an agent knows exactly what disappears, distinct from create_credit, get_credit, list_credits.

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 an explicit precondition step ('check it with get_credit first') and states the credential/scope and claimed-workspace requirements, including the concrete 403 failure mode for sandbox keys.

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