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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, yet the description still adds ordering (most-hit first), the returned fields (last seen, referring site, suggested fix), the full fix taxonomy with semantics for redirect/create/ignore, and an explicit 'changes nothing on the site' reassurance.

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?

Purpose and scope are front-loaded in the opening clause, and every clause carries information (inclusion rule, ordering, fix types, handoff, exclusions). It is a single very long sentence-heavy paragraph though, and the fix taxonomy could be set off as a list for faster scanning.

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?

No output schema exists, so the description must describe return content, and it does: ranking, last-seen time, referring site, and per-row suggested fix. Combined with the fix handoff and exclusion rule, an agent has everything needed to call this and interpret results.

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?

At 67% schema coverage, site_id and user_goal are already documented in the schema and the description adds nothing to them. The limit parameter is undocumented in both places, and 'most-hit first' hints at ordering but not at how limit truncates the result. Baseline 3 is appropriate.

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 concrete verb and resource (addresses that returned 'not found' on the live site) plus the exact inclusion boundary: no page, no redirect, no tracked link. That boundary alone tells an agent how this differs from list_redirects, list_links and validate_links without opening any schema.

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 routes the agent: read here, then 'Carry the fixes out with fix_missing_addresses.' It also states when records will not appear ('Addresses already fixed or left alone are left out'), which is a when-not rule an agent can act on directly.

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