Audition candidate models for a role

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

With no annotations, the description carries full responsibility, and it delivers: parallel probes, mechanical scoring criteria, ranked table plus raw replies, no side effect on recruitment, $0 local models, local-only dropping remote candidates, and non-running hosts reported with their start command rather than errors. It also flags cost implications for judges.

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 long but front-loaded with behavior and returns, and its conditional usage clauses are packed efficiently. It could be tightened into bullets for scanning, but no sentence is obviously wasted.

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 9-parameter tool with no annotations and no output schema, the description covers the core behavior, return shape, side effects, cost hints, and local-model edge cases. It does not describe the exact columns of the ranked table or offer-card schema, but leaves enough for an agent to call correctly.

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%, so the baseline is 3. The description adds helpful cross-parameter context (role triggers offer cards, include_local/local_only control local discovery, judges cost extra calls), but it largely echoes the schema rather than adding substantial new meaning.

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 names a specific action (send one cheap probe to each candidate model in parallel, score replies mechanically) and resource (candidate models), and the return (ranked table plus raw replies). It also distances itself from recruit with 'Recruits nobody — you pick, then call recruit', so an agent can distinguish it from the closest sibling.

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 explicitly states when not to consider the job done ('Recruits nobody') and names the alternative step ('call recruit'). It also gives conditional usage guidance: pass role for offer cards, pass include_local or local_only to probe local models. This is explicit, actionable routing.

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