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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering the safety profile. The description adds that it 'returns' a tool and args, reinforcing no side effects, but does not go significantly beyond the annotations. Baseline 3 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 highly concise, using two sentences to explain purpose, state-based routing, and the return value. The key phrase 'What should I do next?' is front-loaded, and every word adds value.

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 simple, non-destructive recommendation tool, the description covers the necessary context: what it does, how it determines the recommendation, and what it returns. It does not detail the output schema, but that is not required given the tool's simplicity.

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 tool has zero parameters, and the schema description states 'No arguments — the owner is derived from the authenticated principal.' This provides meaningful context for why no arguments are needed, exceeding the baseline for a no-param tool.

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 tool recommends the next action based on the user's current state, with explicit examples (unregistered → register, unverified → start admission, verified → accept work). It also distinguishes itself from the catalog of sibling tools by being a one-call shortcut.

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 tells when to use it (when unsure of next step based on state) and contrasts with reasoning over the full catalog, but it does not explicitly state when not to use it (e.g., when you already know the specific tool to call). Still, the state-based conditions are clear enough.

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