Review exact ordered cross-plugin tasks

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, and the description still adds meaningful traits: the operation is entirely local, does not read passwords, does not check provider state, and does not mint a remote approval token. It also states what gets bound (profile label/site/username, request order, packaged schemas), which goes beyond the annotation set.

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 dense sentences, front-loaded with the core action and followed by scope limitations, with no filler. The phrasing is jargon-heavy ('Local native validation/hash', 'packaged schemas'), which costs some readability but wastes no words.

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?

With no output schema, the description must carry the return contract itself, and it only hints at a 'validation/hash' result without explaining what the preview returns or how the hash feeds into submit_site_batch. The boundary clauses are helpful, but for a preview tool the expected output and failure shape are left underspecified.

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 description coverage is 100%, so the schema already documents both parameters, including the tasks min/maxItems and the arguments rule. The description echoes the 1–20 range and gestures at the profile label, adding little syntax or format detail beyond the structured fields; 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?

The description states a concrete function: local native validation/hash of 1–20 CRM/Community writes, which is a specific verb+resource and clearly a preview (not an executor). It does not, however, name or contrast against the obvious sibling submit_site_batch, so the agent must infer the distinction from the name and the word 'local'.

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: 'Local native validation/hash' signals a dry-run step, and the boundary clauses ('No password read/provider state check or remote approval token') define scope. But there is no explicit when-to-use or when-not guidance, and no routing to submit_site_batch as the execute counterpart.

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