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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world. The description adds meaningful context beyond them: the demo keys are public and read-only, and the demos serve as canonical reference implementations. It does not characterize the return shape or ordering, but for a zero-param read that is minor.

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 what demos are, then the read path, then the template path. The mid-sentence enumeration of demo categories is slightly listy but earns its place by telling the agent what kinds of reference code exist.

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?

No output schema exists, so the description carries the burden of previewing return content, and it does so by describing demos as finished lambdas with concrete types and public read-only keys. An agent knows what it will get and what to do next; only explicit pagination/ordering detail is absent, which is negligible here.

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?

There are zero parameters and schema coverage is 100%, so the baseline is 4. The description correctly adds no parameter commentary since there is nothing to parameterize.

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 states the resource (demos, each a finished lambda) and characterizes what they are with concrete examples (REST API, login, websocket game, uploads). It is clear the tool surfaces this catalog, though it never literally says 'returns a list', leaning on the name/title for the verb. It implicitly distinguishes itself from siblings by framing demos as read-only reference code.

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?

Explicit routing: read the closest demo with read_lambda (plus list_files, read_logs) before writing similar code, and use create_lambda with a demo's id as template to start from a copy. This tells the agent both the follow-up action and the alternative path, which is exactly what a catalog tool needs.

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