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

Annotations already flag destructiveHint=true, idempotentHint=false and readOnlyHint=false, so the safety profile is carried structurally. The description adds one genuinely useful behavior beyond that: the new record is created in UNPUBLISH state, so the agent knows creation and going-live are separate steps. It says nothing about duplicate/path-collision behavior, required website scoping, or permissions.

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?

Two tight sentences, front-loaded with the action and the resulting state, no filler. It is efficient, but the terseness is partly the cause of the parameter gaps rather than a virtue in isolation.

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 8-parameter mutation tool with 0% schema coverage and no output schema needs more than this. The description covers the website selector and the returned IDs but leaves mode/slug/path/url/utm semantics — the core of what a redirect is — undocumented anywhere, so an agent cannot confidently populate the request.

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 description coverage is 0% and the schema provides only property names, so the description carries the full burden — yet it only clarifies two of eight parameters (website_id vs website_uuid) and the returned identifiers. The critical fields seliee_redirect_mode (default SLUG), seliee_redirect_path, seliee_redirect_slug and seliee_redirect_utm are left entirely unexplained, as is the interaction between mode and path/slug.

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?

Specific verb (create) and resource (seliee_redirect), plus the helper qualifier that the record starts as UNPUBLISH. It does not name edit_redirect/get_redirect/list_redirects as the alternatives, but 'create a new' is distinct enough from those siblings to route an agent correctly.

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?

Usage is only implied: 'create a new' signals this is for new records rather than editing, and 'starts as UNPUBLISH' hints that a follow-up publish step exists. There is no explicit when-not guidance (e.g., use edit_redirect instead of re-creating, or what happens if a redirect already exists at that path).

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