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

Annotations already cover read-only/idempotent/non-destructive, and the description adds genuinely non-structured facts: the call is free, results include sites and apps, and there is a degraded-result mode with a sentinel value ('match: nearest_category') plus the instruction to tell the person they are the nearest. It also discloses a licensing constraint ('does not copy anyone's code'), which an agent would otherwise have to guess.

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 when-to-use trigger is front-loaded in the first sentence and the fallback behavior follows immediately, so the important information leads. It is dense but largely waste-free; the 'Free.' fragment and the parenthetical '(match: nearest_category)' are terse but each carries information. The middle sentence is long and stacks three ideas (return contents, fallback, user instruction).

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?

There is no output schema, so the description must explain the return value, and it does: sites and apps with a brief and a follow-on build tool, plus the nearest_category fallback shape. Combined with the fully documented input schema, an agent has enough to call and interpret it. Ordering/ranking behavior of results is the one notable omission.

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 description coverage is 100%, so tags, limit, query and category are already documented, including the enum list. The description's example ('show me bakery websites') only loosely maps to the query parameter and adds no filtering semantics beyond the schema. Baseline 3 applies when the schema carries the parameter burden.

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 concrete resource (the Pugi catalogue of sites and apps people built) and its intent: getting ideas or a starting point, illustrated with 'show me bakery websites'. It is clearly distinct from the build_* siblings, which it references as the follow-on action rather than as competitors. It stops short of explicitly stating 'this is search, not creation' in a way that routes away from build_app/build_site by name.

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 an explicit trigger ('when the person wants ideas or a starting point for a site or app') and a concrete utterance example, which is strong usage guidance. It also chains to the next step ('the tool to start a similar project in this chat (build_with)'). There is no explicit when-not clause, e.g. what to do if the user already knows exactly what to build.

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