squiggle: Get sources

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

Annotations already declare readOnly, idempotent and openWorld, so the safety profile is covered. The description adds non-obvious behavioral context beyond that: the returned ids are reusable as keys in the tips and ladder tools, which tells the agent this is a lookup/enumeration step rather than a terminal call.

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 short sentences: the first defines the resource and its contents, the second states the downstream usage. Zero filler, and the purpose is front-loaded.

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 small read-only enumeration with rich annotations and a fully documented schema, the description covers what it lists and how the output is consumed. It omits any note on the optional 'fields' projection or whether the source list is fixed, which are minor gaps.

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% for the single optional 'fields' parameter ('Keys to keep (comma-separated)'), so the schema does the work. The description never mentions projection or the fields parameter, adding nothing on top — baseline 3.

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 (list) and resource (prediction model sources in Squiggle) and enumerates concrete examples (Squiggle, MoS, FiveThirtyEight). This cleanly separates it from the sibling squiggle_get_teams / get_games / get_ladder tools, which return entirely different resources.

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?

Explicitly routes the agent downstream: 'Use the returned ids with tips and ladder tools,' naming the two sibling tools that consume this output. It gives clear when-to-use context but no when-not or exclusion conditions.

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