list_pending_approvals

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

With no annotations, the description carries the burden of behavioral disclosure. It explains that approval is human-controlled, that the key drafts rather than sends, and that retrying is wrong. It does not mention whether the list is scoped to the current key or describe pagination/return envelope, but core behavior is clear.

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 concise sentences with no filler. Each sentence earns its place: what the tool lists, why messages are pending, and an operational warning about retrying sends.

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 zero-parameter list tool, the description covers what it returns, the approval workflow context, and the key behavior to avoid. It could be slightly fuller by pointing to decide_approval for taking action on the pending message, but it is otherwise complete.

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 schema coverage is 100%, so no compensating description is needed. The baseline of 4 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 opens with a specific verb and resource: 'List messages held for human approval', and adds 'with their full content'. This clearly distinguishes it from sending tools and from decision tools like decide_approval.

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?

It gives an explicit trigger condition: after a send returns 'pending_approval', the message is waiting here and the send should not be retried. It does not explicitly name decide_approval as the tool for resolving approvals, which keeps it from a 5.

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