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

Goes well beyond the annotations: discloses the fallback chain, that unmatched pages land on the homepage and are flagged needs_look, that manual redirects are preserved, and that the call takes up to a minute. No contradiction with idempotentHint=true or destructiveHint=false.

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-loaded with the action and dense with useful conditional detail, but the single long sentence with nested em-dashes and parentheticals takes effort to parse. Little is wasted, though the 'For a redesign:' preamble is slightly redundant with the title.

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 mutating tool with no output schema, it covers triggers, resolution logic, the needs_look signal, and runtime. Minor gap: it doesn't say what the caller gets back (how many redirects created, whether conflicts are reported), so an agent can't anticipate the result shape.

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 the schema already documents all three parameters. The description adds the deciding condition for `old_site_url` (use it when the old site was never recorded), but says nothing about `site_id` or `user_goal`, so it sits at the baseline.

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: read every address from the old site's sitemap and homepage links and 301-redirect each to the closest page on the new site. The fallback resolution order (same page → same item → section → homepage) further pins down the exact behavior, distinguishing it from siblings like add_redirects or validate_links.

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?

Explicitly covers when it fires on its own (after a redesign is generated and when built), when to invoke manually (after big page changes, or with `old_site_url` when the old site was never recorded), and a hard exclusion (hand-set redirects are never modified). Nothing is left to inference.

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