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

Adds substantial behavior beyond the annotations: read-only unless backup=true, the backup is skipped while another backup is running, best_effort means every step runs independently, 'No undo', and — critically — that through Royally nothing changes on the site until a person approves it. That human-in-the-loop gating and the conditional write path are exactly the context annotations alone cannot convey.

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 purpose, then the behavioral caveats and the Royally approval note. It is dense and largely earns its space, though the compose_mode default and backup skipping are restated from the schema descriptions, adding mild redundancy.

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 composite rollup with no output schema, the description covers the write path, failure semantics, and approval gating well. The main gap is that it never hints at the shape of the returned findings (aggregated report vs per-check sections), which would matter for a multi-step audit.

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 baseline is 3, but the description earns extra by stating the default compose_mode=best_effort and that backup=true queues a SiteVault backup with skip-while-running semantics — behavior the enum/boolean types do not express. It does not elaborate on strict vs report_only beyond what the schema text already says.

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 states a specific verb and resource ('site-readiness rollup') and then enumerates the exact sub-checks it composes: SEO audit, broken-link scan of same-origin home-page refs, TTFB perf, security status. That enumeration lets an agent distinguish it from single-purpose siblings like wp_security_triage, seo_audit_meta_tags, or recipe__run_site_health 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?

Usage context is clear from 'site-readiness rollup' plus the pre-launch name, and the description explains the compose_mode default and what backup=true does. It stops short of naming an alternative or an explicit when-not-to-use condition (e.g. 'use wp_security_triage if you only need security status'), so it lands just below the top tier.

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