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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds material context: the entire rule set is replaced (not merged), evaluation occurs server-side before render, and path/URL format rules. It stops short of saying what happens to existing rules on partial failure or whether a publish step is needed.

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 sentences, no filler, with the destructive full-replacement semantics and evaluation order front-loaded. Every clause carries operational meaning.

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 destructive, idempotent bulk-write tool with full schema coverage and no output schema, the description covers the essential semantics (full replacement, evaluation timing, path/URL rules). It omits failure-mode behavior and the 500-rule cap is left to the schema, so a small gap remains.

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%, so both parameters and the nested from/to/permanent fields are already documented, making 3 the baseline. The description's note that paths are site-relative and destinations may be absolute URLs largely restates the schema's own field descriptions.

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?

A specific verb ('Replace') plus resource ('301/302 redirect rules') and a scope note ('evaluated server-side before render') tell the agent exactly what operation happens. It does not explicitly differentiate itself from the adjacent set_domain_redirect_mode sibling, which keeps it from a 5.

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?

'Replace' plus the schema's 'Pass the full list' signals the full-overwrite usage model, so the agent can infer this is not an append/patch call. However, there is no explicit when-to-use guidance, no mention of the alternative (set_domain_redirect_mode), and no note about prerequisites such as site selection or publish requirements.

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