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

Goes well beyond the annotations by disclosing the approval flow ('always waits for approval, only a workspace admin's approval applies it'), the overwrite semantics ('it replaces the list'), and the timing of effect ('the next run reaches the new list'). These are critical behaviors an agent cannot infer from readOnlyHint=false/openWorldHint=true alone.

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?

Front-loads what the tool does and packs required format, workflow, and approval details into a tight paragraph. Slightly long in the middle clause about using a site 'like a person would,' but essentially every sentence carries actionable 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 4-parameter mutation with no output schema and full schema coverage, the description covers purpose, format, replacement semantics, approval requirements, and effect timing. The only minor gap is error/failure behavior beyond the approval path, but the definition is otherwise complete enough to call correctly.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds value: it shows the format syntax (example.com vs *.example.com for subdomains), reiterates the 20-item cap, and clarifies that sites is a full replacement set ('pass every site to keep').

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 specific verb and resource ('Sets the full list of sites a routine's machine may reach') and explains the trigger condition versus read_webpage. It does not explicitly distinguish itself from the similar sibling workbench_tasks_set_sites, leaving a small ambiguity for tool selection.

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?

Explicitly names when to use it ('a routine that has to use a site like a person would because read_webpage can't get it') and the alternative that fails. It also gives a prerequisite workflow ('read routines_list first and pass every site to keep'), so the agent knows both when and how to act.

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