jev_models

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

No annotations are supplied, so the description carries the full behavioral burden. It does disclose several traits the annotations would otherwise cover: the return shape (list of dicts, collapsing to a single-element list when a filter is applied) and the failure mode (raises ValueError when nothing matches). However, it says nothing about read-only semantics (implied but not stated), whether the registry is remote or local, or whether calls are rate-limited or cached. For an unannotated tool, this is a meaningful gap.

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 content is front-loaded (what it lists, then filtering behavior, then the error case, then the provider parameter), and every sentence carries information. Minor noise comes from docstring markup such as :func:`daf_jev.models.pick_model` and the unbalanced closing conditions, which read as references to internal code rather than agent-facing guidance.

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?

The tool is simple (three optional parameters, no required arguments), and an output schema exists, so return-value documentation is not strictly required. The description nonetheless covers filter interaction, the error path, and the provider default, which is nearly everything needed. The only real omission is whether the operation is a safe read with any side effects or authorization requirements.

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 0%, so the description must compensate, and it does: it explains pick's selection semantics and its effect on the result shape, defines contains as a case-insensitive substring filter with the empty string meaning no filter, and identifies provider as the registered API provider with a default of jev. Every parameter receives meaning that is absent from the bare schema.

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 first sentence states a specific verb and resource (list available model cards as dicts), and the rest clarifies the filtered variant of that same operation. It does not mention any sibling tool, but the siblings (jev_ask, jev_evaluate, jev_tiered_gate) are conceptually far enough apart that confusion is unlikely.

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 description implies when the filter path activates ("When pick ... or contains ... is given"), which is useful usage context. It never says when an agent should prefer this tool over querying a specific card elsewhere, and gives no prerequisites or exclusions.

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