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

Beyond the readOnly/idempotent/non-destructive annotations, it discloses that design-source rows are folded by default, that pagination is driven by `total`/`has_more`/`next_offset`, and that each call opens another gallery in interactive hosts — a real side effect an agent must know about. It also enumerates exactly what each row contains, so the agent knows what it gets back without an output schema.

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?

Purpose and the trigger condition are front-loaded, and every sentence carries operational content. There is some redundancy between 'Reuse the site_id of a matching site already returned' and the closing 'Do not repeat list_sites or expand source designs when that site is already identified', which could be merged into one statement.

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 six-parameter, zero-required listing tool with no output schema, the description covers pagination, default filtering, field-level return shape, fallback tools, and exclusions. An agent has everything it needs to decide whether to call and how to iterate pages.

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; the description earns above that by explaining intent for `query` (match a named site instead of paging), `offset` (= `next_offset`), and `include_design_sources` (true when you need to choose or inspect those designs). It does not touch `limit`, `status`, or `user_goal`, but those are well documented in the schema.

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 and resource plus scope and ordering ('List the sites in the user's Mondovo account, newest first, one page at a time'). It explicitly routes away from siblings by naming get_site for pages and list_variations for designs, so an agent can distinguish it from the ~250 other tools without opening a schema.

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?

Gives a positive trigger (user asks to browse/find sites, or an unknown site_id is needed) and an explicit exclusion list (onboarding, greetings, capability questions, keyword-only demand checks, auto-calls before a new build). It also names the substitute path: pass `query` instead of paging through everything, and reuse a site_id already returned rather than calling again.

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