Recommend a model for a task

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description goes beyond that by disclosing a genuine filtering rule: 'Never recommends models RealRun flagged as not recommended.' It still omits whether results are ranked, single, or include reasoning, so it adds value but not full behavioral context.

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 with zero filler; the purpose and its decision input are front-loaded, and the exclusion rule is stated compactly at the end.

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?

There is no output schema, so the description carries the burden of explaining what comes back, yet it never says whether a model id, a ranked list, or rationale is returned. For a simple read-only recommendation tool this is adequate but leaves a real gap around the response shape.

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 all three parameters are already documented. The description restates the priority enum values ('accuracy', 'cost' or 'balanced'), which is redundant rather than additive, and says nothing extra about task or include_subscription. Baseline 3 is appropriate.

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 and resource ('Recommend which AI model to use') plus the input that drives the choice ('given a priority'). The sibling tools (get_scores, get_warnings, list_tasks) are clearly unrelated, so an agent can identify this tool's role without ambiguity.

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?

Names the deciding input and enumerates its allowed values, which implies when the tool is useful (choosing a model by priority). However, it gives no when-not guidance and does not point to any alternative tool for related questions (e.g., why a model was excluded), leaving usage to inference.

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