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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds a genuine behavioral constraint (models flagged as not recommended by RealRun are excluded), but it does not describe what the recommendation looks like, how many models are returned, or whether it is ranked — a gap since there is no output schema.

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 tight sentences with the core purpose front-loaded and no filler. The exclusion policy in the second sentence earns its place, though the phrasing 'RealRun flagged' is slightly opaque.

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 three params, no output schema, and only read-only annotations, the definition is adequate but incomplete: an agent cannot tell what a recommendation returns or how to act on it. The exclusion policy is a useful addition but does not close the return-value gap.

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 schema already documents task, priority, and include_subscription, including enums and defaults. The description restates the priority values but adds no format, constraint, or interaction detail beyond the schema; 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?

States a specific verb (recommend) and resource (AI model) and names the inputs that drive the choice (task + priority). It is clearly distinct from the sibling read-only tools (get_scores, get_warnings, list_tasks), though it never explicitly contrasts itself with them.

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?

Usage is implied by 'for a task given a priority' and the enumeration of priority values, but there is no explicit when-to-use/when-not guidance or reference to alternatives. The one stated constraint (never recommends flagged models) is a policy, not a usage rule.

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