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

The description adds two facts the annotations do not carry: credentials are stored sealed and never returned, and unconnected site types are rejected. However, annotations declare destructiveHint=true and idempotentHint=false, and the description never says what an existing destination's credentials are overwritten or what re-saving the same kind does, leaving the most consequential behavior unexplained.

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 short sentences with the credential-secrecy guarantee placed early, which is the highest-value fact for an agent. The final sentence about refused site types reads awkwardly but still earns its place as a pre-condition warning.

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?

A 7-parameter mutating tool flagged destructive with no output schema and only 43% schema coverage needs more: behavior on re-save, required credential combinations per kind, and the unsupported `wix` option are all missing. An agent could invoke this and be surprised by what it overwrites or refuses.

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 43% schema coverage the description must compensate, and it partly does by pairing credential types with site kinds (WordPress appPassword vs Shopify token vs page). It omits `label`, `blogId`, `username`, and the `wix` kind entirely, so several parameters remain undocumented in both places.

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 verb 'Save' plus the resource (a WordPress site, Shopify shop, or page destination) is concrete and the sibling soclo_articles_destinations_list sits clearly on the read side. It loses a point because the enumerated `kind` values include `wix`, which the description never mentions, so the stated scope is narrower than the actual tool.

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?

There is no explicit when-to-use or when-not guidance, and no alternative is named even though soclo_accounts_connect and soclo_destinations_list exist in the same namespace. The only conditional statement ('a site type that is not connected yet is refused') describes a failure mode, not a selection rule.

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