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

Annotations already flag destructive and non-idempotent behavior, but the description adds materially: no points are spent, non-member calls fail, and content violating the static-site policy (scripts, forms, redirects, frames, password prompts) is refused with an explanatory message. It does not discuss reversibility of delete_file or publish side effects, keeping it short of a 5.

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?

A single dense paragraph that front-loads the core purpose and prerequisites before moving to validation rules. The file-type list is somewhat verbose, but each sentence carries operational information rather than restating the tool name.

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 nested, free-form-parameter mutation tool with no output schema, the description covers prerequisites, spend cost, content restrictions, and a discovery mechanism via "help". Remaining gaps — return shape and failure modes beyond content refusal — are acceptable since an output schema is absent and errors are described in prose.

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 only 50% and params is an open free-form object with additionalProperties true, so the description carries real weight: it lists the enum values in prose and, critically, tells the agent to call action "help" to discover each action's fields. That fills the biggest semantic gap the schema leaves open.

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 names a specific verb and resource — building the member's Applystead personal website — and enumerates the concrete actions (write_file, delete_file, publish, connect_domain, disconnect_domain). It clearly separates this mutation surface from the read-only sibling get_website, which an agent can identify from the name 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?

It states the prerequisite (an Applystead membership), clarifies a non-obvious boundary (images are added in the app, not written as files), and routes the agent to action "help" for per-action fields. It does not explicitly say to prefer get_website for reading, so the alternative is only implied.

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