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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds non-redundant context: it proposes fixes but applies nothing, it is time/volume bounded (which affects how long a call blocks), and Royally's server marks it read-only so it executes without an approval gate. These are execution traits the annotations alone don't convey. What's missing is any hint at result shape or failure behavior.

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?

Three compact sentences, front-loaded with what is detected and what the two finding categories mean. Minor waste: 'Read-only — changes nothing' restates readOnlyHint, and the trailing Royally sentence is meta-context rather than tool behavior, though it does carry the no-approval-gate signal.

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 no-output-schema, no-required-params scan tool the description covers purpose, safety posture and run bounds well. It stops short of telling the agent what comes back (per-post findings? proposed replacement URLs?) or that scans may be partial when the max_posts/max_seconds caps are hit, which matters for interpreting 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?

Schema coverage is 100%, with descriptions, ranges and defaults for max_posts (1-2000, default 200) and max_seconds (1-60, default 10), and an enumeated site_id. The description only echoes that the scan is 'bounded by max_posts/max_seconds' without adding format or trade-off guidance (e.g. what raising the limits costs). Baseline 3 is appropriate when the schema carries the semantics.

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 (scans) plus a precisely scoped resource (published content, internal links) and two named defect classes: links to trashed/missing pages and links to paths that already redirect. This is concrete enough that an agent can distinguish it from adjacent link tools (check_broken_links, rank_math_get_404_logs) by scope alone.

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 implied rather than stated: an agent can infer 'run this before fixing internal links,' but there is no explicit when-to-use, when-not-to-use, or named alternative. Given the many sibling link/redirect tools in this fleet, at least one routing sentence would have real value.

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