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

Annotations already declare non-read-only, non-idempotent, non-destructive, closed-world behavior. The description adds the critical extra fact that this is asynchronous ('Enqueue... resolves'), which no annotation conveys and which changes how an agent should treat the call. It does not say how to poll status or whether repeat calls spawn duplicate runs.

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 tight sentence, front-loaded with the action verb and the async nature, with no filler.

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 one-param job-trigger tool with annotations covering the safety profile and no output schema, this is nearly complete. The remaining gap is that it doesn't indicate how the resulting run is observed or that non-idempotent repeats create separate runs.

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 schema coverage is 100%, so the schema already fully documents site_id as a site UUID. The phrase 'for a site' adds only marginal confirmation. Baseline 3 applies when the schema does the work.

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 (enqueue) plus resource (keyword-rankings sweep) and scope (one site, all tracked keywords' SERP positions). This clearly separates it from the read-side sibling get_keyword_rankings, though it never names that sibling explicitly.

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: you call this to trigger a fresh sweep, versus get_keyword_rankings to read stored positions. No explicit when/when-not conditions, prerequisites, or named alternatives are provided.

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