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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds real value by disclosing the eligibility condition (two-person shut-off must be enabled and the request must be awaiting a second approver), but says nothing about ordering, completeness of the list, or whether it paginates.

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?

A single front-loaded clause with no filler; every element (resource, pending state, approver roles, two-person condition) carries meaning. It is a sentence fragment rather than a full statement, which is terse but not wasteful.

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 no parameters, a declared output schema, and annotations covering safety and world scope, the description only needs to define what set of records is returned — and it does. Ordering/pagination details are the only meaningful omission, and those matter less for a small approval queue.

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 takes zero parameters, so there is nothing for the description to disambiguate beyond the implicit scope, which it already supplies via the approval-state filter. Baseline for a no-param tool 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?

The description names a specific resource (shut-offs) and a precise filter (those awaiting a second owner/admin/security approver under two-person shut-off), which is far more informative than the title's 'Shut-offs waiting'. It does not explicitly contrast with siblings like confirm_shut_off or shut_off_key, so the agent must infer the relationship rather than being told.

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 conditional framing ('waiting for a second owner, admin or security member') implies this is the queue-inspection tool for pending two-person approvals, but it never states when to call it or that confirm_shut_off is the follow-up action. Usage 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.