lbb_model_choice

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

Annotations only declare readOnlyHint=true, and the description reinforces 'read only' consistently while adding substantial context: what options shows (current/default/switched, key availability, available=false with a reason), what trials reports (delta, ci interval, outcome values, the qualifies bar), and that results are newest-first. It stops short of documenting auth/rate-limit or pagination traits, so 4 rather than 5.

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 description is a dense run-on paragraph with no line breaks or front-loading; the single-sentence opening is buried in clauses about ground truth and checked calls. Information is relevant but the structure makes it hard to scan, which is a conciseness/structure failure rather than under-specification.

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?

With no output schema, the description carries the return-value burden and does so thoroughly (per-action outputs, outcome enum meanings, the qualifies criteria). Combined with 86% schema coverage and readOnlyHint, an agent has enough to call it correctly; only minor gaps like pagination/ordering for non-trial actions remain.

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 86%, so the schema already documents job, limit, call_id, trial_id, graph, and detail. The description only loosely ties fields to actions (e.g., 'newest first' matching limit) and adds no syntax or format meaning beyond what the schema provides, so the baseline 3 applies.

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 a specific verb+resource ('Model choice, read only') and enumerates exactly what each action exposes (options, trials, trial, trial_call, switches). It also explicitly distinguishes itself from the sibling mutation tool lbb_model_choice_manage, so an agent can tell the two apart without opening a 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?

It gives clear routing guidance for the write path ('Start, stop, switch or revert with lbb_model_choice_manage') and describes what each read action returns, implying when each is used. It does not give explicit when-not conditions or a crisp decision rule among the five read actions, so it falls short of a 5.

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