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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds valuable behavioral context beyond annotations by noting that the score is 'null until scored', and describes the return structure (per-criterion scores, justifications, follow-up questions). This goes beyond the annotations, so a 4 is appropriate.

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 single, well-structured sentence that front-loads the action and states return contents and null behavior. There is no waste; every clause contributes essential information.

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?

Given the simple one-parameter tool, annotations for read-only safety, and no output schema, the description is nearly complete. It covers the purpose, return contents, and null-score state. It does not explicitly mention error handling for an invalid ID, but that is standard for a getter and not required. The description sufficiently equips an agent to call it 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?

The schema provides only a single 'id' field with no description (0% coverage), so the description must clarify its meaning. While it does not explicitly state 'id is the application ID', the phrasing 'Get the AI score of an application' makes it clear that the single parameter refers to the application. This adds meaning beyond the bare schema, justifying a 4.

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 clearly states the specific verb ('Get') and resource ('AI score of an application'), and enumerates the return contents ('per-criterion scores, justifications and follow-up questions'). It effectively distinguishes from the sibling 'hires_get_evaluation' by narrowing to the AI score specifically.

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 to use the tool (when you need the AI score) but does not explicitly mention alternatives or exclusions. No guidance is given on when not to use it (e.g., if you need a human evaluation, use hires_get_evaluation instead). The usage context is implied rather than stated.

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