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

Annotations already signal destructive and non-readonly behavior, and the description adds valuable context beyond that: archiving blocks public submissions and cannot be undone in v1. This directly informs the agent about irreversible consequences, which is exactly the kind of behavioral detail needed.

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 no filler: purpose, side effect, and irreversibility warning are all front-loaded. Every sentence earns its place.

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 one-parameter tool with a well-described schema and annotations already covering safety and idempotency, the description is complete. It tells the agent what happens, what not to use it for, and what cannot be done afterward.

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?

The input schema already fully documents project_id with format, pattern, and valid sources (list_projects, create_project, bootstrap_site). The description adds no parameter-specific detail, so the baseline 3 applies because the schema carries the parameter 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?

The description states a concrete verb and resource ('archive a website') and gives the key consequence ('Archived projects reject public submit'), so an agent can recognize it as the project-archiving action. It does not explicitly differentiate from sibling tools like archive_client or archive_form, but 'website' and 'projects' make the intended resource reasonably clear.

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 provides clear when-to-use context: use it to archive a website, and it explicitly warns not to treat it as a hard delete. It also notes the critical v1 limitation that no unarchive tool exists. It stops short of naming alternative tools or specifying when to prefer update_project or archive_client, but the guidance is still actionable.

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