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

Annotations already mark destructiveHint=true and idempotentHint=true, and the description reinforces the destructive action by warning that the previous short URL stops redirecting and the QR image is regenerated. It adds value by explaining the consequence of printed/shared copies needing replacement, which goes beyond the annotations. Since the destructive hint is present, a 4 is appropriate—it enriches the context without repeating the annotation.

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 concise and front-loaded: it states the core action with an example, then routes to alternatives, and ends with a warning. The warning is necessary for safe usage, and the sentences are efficient. Slightly verbose with the WARNING tag, but it earns its place given the destructive nature.

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?

Given the output schema exists, the description need not explain return values. The tool is a mutation with clear side effects; the description covers the key consequence (old URL stops redirecting) and regeneration of QR, which is critical for an agent. It lacks details on error cases (e.g., slug not unique) but that is implied by the schema. Overall, it is sufficiently complete for an agent to use correctly.

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 input schema provides 100% coverage with detailed descriptions for both parameters (qr_id as stable identifier, short_code with pattern and uniqueness requirement). The description adds the example 'summer-sale' and notes the slug must be unique within the domain, but this largely overlaps with the schema. Baseline 3 is correct because the schema already handles the heavy lifting.

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 clearly states the action ('Change the custom slug of an existing QRCodeKIT short link') with a concrete example (qrkit.co/x7Ab9c to qrkit.co/summer-sale), and it distinguishes itself from sibling tools like save_short_link by specifying 'any link type' and preserving identity/analytics. It also explicitly notes it is not for changing the destination, which differentiates it from the various save_* tools.

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 provides explicit guidance on when to use: 'Use this only when the user explicitly wants to rename the short URL.' It also gives a clear alternative: 'to change a destination, use the corresponding save tool instead.' This directly addresses the when/which-tool question, leaving no ambiguity.

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