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

With no annotations at all, the description carries the full behavioral burden, and it does contribute some context: the artifact is a standalone page, it keeps a chat history, and creation is fast ('in a few seconds'). It says nothing about what happens to a pre-existing AI, whether the page can be deleted or modified later (vs. change_site), or whether permissions/auth are involved for a create operation — notable gaps for a mutation tool with zero annotation coverage.

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?

Two sentences, front-loaded with what gets created before the routing guidance. Every clause earns its place: the analogy, the chat-history trait, the page location, the speed expectation, and the exclusion each add distinct information with no filler.

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 one-parameter creation tool this covers what is produced and when to reach for it, which is most of what an agent needs. The main omission is what the call returns (presumably a page URL or identifier) and whether calling it again creates an additional AI or overwrites the existing one; with no output schema and no annotations, those points would have been worth one more clause.

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% and the schema already documents 'about' with a concrete example, so the schema does most of the work. The description still adds real scope meaning with 'for one job', clarifying that the about value should describe a single narrow purpose rather than a broad multi-purpose assistant — a constraint the schema text does not state.

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 concrete verb+resource (make a simple chat AI) and immediately bounds it with an analogy ('like a small ChatGPT for one job, with a chat history') and a scope constraint ('on its own page'). The closing phrase 'not a website' separates it from the closest sibling, make_website, so an agent can pick between them without opening either 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 an explicit positive trigger ('use when the user wants just an assistant') and an explicit negative one ('not a website'), which is the main routing decision for this family of tools. It stops short of naming make_website or the other siblings directly, so the agent must map 'website' to the sibling itself, but the intent is unambiguous.

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