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

Annotations declare non-read-only, idempotent, non-destructive, but the description adds traits they cannot express: the served files are not modified, an already-sourced site is untouched, and force mode copies minified build output that is not original source. That last point surfaces a real consequence and a consent requirement beyond the structured hints.

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 sentences, front-loaded with the outcome and precondition, then consequences, then the caveat. No filler and nothing repeated from the name or schema.

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?

An output schema exists, so return values need not be described, and all three parameters are documented in the schema. The behavioral and usage context needed to invoke this safely (precondition, no-op case, force-mode risk) is fully covered.

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 100%, so the baseline is 3, and the description does add value by tying the mode parameter to a behavioral rule ('force only after telling the user that build output is not original source'). It does not further clarify name vs siteId, which the schema already handles.

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?

States a specific verb (create/copy) and resource (the editable source tree) with an explicit precondition: a site that has none. It also names the downstream tools (write_source_files, apply_edits, build_and_deploy) that exist only after this runs, which cleanly separates it from siblings like list_source_files or write_source_files.

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 the exact condition for use ('a site that has none'), the no-op case ('a site that already has source is left as is'), and a conditional rule for the risky path ('use mode force only after telling the user...'). That is when-to-use, when-not-to-use, and a gating instruction in one place.

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