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

Annotations already cover readOnly, idempotent, non-destructive, and closed-world, so the description only needs to add behavioral texture. It does: it explains the returned shape (per-key `type` and `example`) and the all-or-one behavior when a key is omitted. It doesn't discuss pagination or ordering, which is a minor gap.

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 sentences, no filler, with the resource and the parameter rule front-loaded. The parenthesized key examples are useful, though the first sentence is slightly dense with nested naming (`seliee_website`, `seliee_website_options`).

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?

There is no output schema, yet the description compensates by describing what each entry contains (`type`, `example`) and the default all-keys behavior. Combined with the annotation-covered safety profile, an agent has enough to invoke it correctly; only ordering/pagination details are unaddressed.

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 0%, so the description must carry the parameter meaning — and it does: the optional `seliee_website_key` selects one key, omission returns all, and the example `seliee_website_contact_email` anchors the format. It stops short of stating alternatives for the website scope (whether key is the website or the option key), leaving minor ambiguity.

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 gives a specific verb+resource: it enumerates the keys that a seliee_website's `seliee_website_options` map accepts, with each entry's `type` and `example`. It clearly establishes this as a read-only schema/discovery lookup rather than a data fetch. It doesn't name or distinguish itself from adjacent metadata tools (e.g. get_website_keys / update_website_keys) by name, so it falls short of 5.

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?

It gives a clear rule for the parameter ('Pass a key for one entry; without a key, returns every option'), which makes the calling pattern obvious. However, it offers no explicit when-to-use guidance against siblings such as get_website or get_website_faqs, nor any stated prerequisites (e.g. needing a website already created).

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