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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the mutating nature is covered. The description earns credit by adding context beyond them: 'Nothing is charged' reassures about billing impact despite the destructive flag, and the admin-only restriction discloses an authorization requirement not in the schema.

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 with the core action front-loaded; little waste. 'reason is optional' duplicates the schema's own optional typing, costing a small amount of redundancy.

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 two-parameter mutation with no output schema and annotations carrying the safety profile, the description covers scope, billing impact, and authorization. The remaining gap is that it does not indicate how to discover a valid request_id (e.g., via a listing tool) or what state the request ends in.

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 50%: the reason parameter is already documented in the schema, and the description merely restates its optionality. request_id is undocumented in both places, and the description does not say where to obtain a valid request_id or its format, so it adds little meaning 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 — 'Declines one open membership upgrade request' — plus the cardinality ('one') and the constraint that the request must be open. This separates it from approve/cancel style siblings, though it does not name them explicitly.

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?

'Only an account admin can decline' establishes a prerequisite for use, and 'one open ... request' implies the preconditions. However, there is no explicit guidance on when to decline versus cancel, or what to do if the request is not open, leaving selection logic partially to inference.

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