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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds real value beyond them with the 'newest first' ordering and the explicit scope exclusion ('Never the approval's message or answers'), which tells the agent it cannot retrieve approval content here. It stops short of saying how the 'expires or continues' timestamp should be interpreted or how continued waits drop out of the list.

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 sentence: verb and resource first, then temporal ordering, then the payload fields via a colon list. The field enumeration is long but each item carries information an agent would otherwise have to guess, since there is no output schema.

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 read-only, single-parameter list tool with no output schema, the description supplies the return-shape information that would otherwise be missing and flags the one important data exclusion. Only minor gaps remain: no mention of result limits/pagination in practice or what happens when there are zero open waits.

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?

Only one parameter, and its schema description is already 100% covered, including the default of 20 and the 1-100 bounds. The description of the tool adds nothing about limit or pagination behavior, so the baseline of 3 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?

Specific verb plus resource ('Lists the open waits'), and it defines the otherwise opaque domain term by naming the three underlying step types (approval, delay, callback). It also names the exact fields returned, so an agent can distinguish it from list_runs/get_run without opening the schema.

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?

Usage is implied rather than stated: the field list and the three step kinds make clear this is the tool for finding pending approvals/delays/callbacks, but there is no explicit 'use this when' or 'use get_run instead for X' routing. None of the sibling tools are named.

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