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

Even though idempotentHint is already annotated, the description adds important caveats: idempotent on slug unless strict is true, plan_limit error signaling, free-account footer_mode restrictions, and token rendering behavior where missing fields render empty and never error. It also warns not to pass HTML and not to expose the files URL in a public snippet.

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?

The description is accurate and dense but not concise; it is a long block of prose covering plans, upgrade links, email tokens, uploads, and branding, much of which could be trimmed or structured. The key create_project-specific guidance is front-loaded, but the latter half reads more like general platform documentation than focused tool usage.

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 22-parameter tool with no output schema and minimal annotations, the description is remarkably thorough: it covers idempotency, plan limits, email templating, upload behavior, upgrade routing, and security warnings. The main gap is that it does not describe the successful return payload shape, aside from mentioning plan_limit and returning the existing record on idempotent re-runs.

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%, but the description still adds meaning far beyond the schema: strict changes idempotency behavior, email templates support specific tokens like {{project.name}} and {{count}}, footer_mode off is unavailable on free accounts, uploads_enabled must be set before accepting files, and file inputs use multipart POST. This materially helps an agent use the parameters correctly.

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 opens with a specific verb and resource: 'Use to add one website under an existing client_id.' It also explicitly differentiates from a sibling by saying 'Prefer bootstrap_site when the client does not exist yet,' which is exactly the kind of sibling distinction an agent needs.

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?

The description gives clear routing guidance: use this when a client already exists, prefer bootstrap_site when the client does not, and on plan_limit call create_upgrade_link and hand the Stripe URL to the human. It also explains plan restrictions that determine when this tool can be used.

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