examples

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

With no annotations, the description carries the burden, and it does convey that examples are real analyses 'run node by node with the same tools and pauses as any other', which tells the agent what it is browsing. It says nothing about whether invoking it is a read-only lookup, how large the result is, or any cost/latency characteristics.

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?

Reasonably short and front-loaded with 'The worked examples that come with sima', but the middle clause ('from the univariate models built in art, run node by node with the same tools and pauses as any other') is discursive and uses unexplained jargon ('art'), diluting rather than clarifying.

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?

An output schema exists so return structure needn't be explained, and the description gives conceptual grounding on what examples are. Still missing: an explicit statement of what a call yields (a list of example names/descriptions) and a clear handoff that those names are the inputs to `load_example`.

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?

Zero parameters gives a baseline of 4. The description adds a small bonus by naming the `<name>` argument of the related `load_example` call, so the agent understands the output of this tool feeds that parameter, though it never explicitly says the examples' names are the return values.

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 identifies the resource (worked examples shipped with sima) and hints that each is a real run-through analysis, but it never states what invoking `examples` itself does — presumably returning a catalog of examples — nor what the caller gets back. It does distinguish itself from the sibling `load_example`, which 'starts one', so an agent can partially infer the split.

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 final clause 'load_example(<name>) starts one' routes the agent toward the follow-up tool, implying `examples` is the discovery step. However, there is no explicit 'use this when…' framing, no mention of prerequisites, and no statement that this tool is the place to get valid `<name>` values.

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