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

Goes well beyond the annotations by disclosing system-wide side effects (nothing is sent to AI and match scores are hidden while off), a credit cost per ranked application, and an admin-only authorization requirement. These are exactly the consequences an agent needs before flipping a company-wide switch.

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?

Three short sentences, no filler: the action and scope come first, then the off-state consequences, then the conditional parameter and the permission gate. Every sentence carries distinct 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?

For a non-idempotent, non-destructive mutation with no output schema, the description covers side effects, cost, and authorization. It does not say what happens to previously computed scores when it is switched off, which is the main remaining question for a state-toggle tool.

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 description compensates for the 50% schema coverage on `waiting` by explaining the two options in plain terms — rank the applications that arrived meanwhile at one credit each, or skip them — and clarifies that the choice is required only when enabling. `enabled` is left to the schema and its boolean name, which is adequate.

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 concrete action (turn AI ranking off/on) on a concrete resource (AI ranking) with an explicit scope ("for the whole company"), which separates it from per-application siblings like rank_application. It does not name the sibling that actually performs ranking (rank_waiting_applications), so the boundary is only implied.

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?

Gives real conditional guidance: when turning it on, the caller must supply a `waiting` choice, and it states the admin prerequisite. It omits explicit when-not-to-use guidance and does not point to the sibling tools for ranking existing applications.

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