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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true), and the description adds genuine behavioral context beyond them: it explains that a scheduled import can copy a Google Ads pause onto Microsoft Advertising at its next run, which is a side effect the agent could not infer from annotations. It omits auth requirements and how to interpret job status values, so it is not exhaustive.

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-loaded with the verb and resource, then the return fields, then the usage trigger — a sensible information order with no filler. The second sentence is long and carries two ideas (the diagnosis scenario and the scheduled-import side effect), but both earn their place.

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 output schema, the description compensates by listing the returned fields (name, status, schedule, last run, creator, source Google account, synced settings) plus the plain-English effects list. What is missing is minor: pagination behavior and what status values are possible, but neither blocks correct invocation of a zero-required-parameter list tool.

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 description coverage is 100%, and the single accountId parameter is fully documented in the schema including the example format and the 'only needed when the sign-in can reach more than one account' condition. The description adds nothing about the parameter, so the baseline 3 for high-coverage schemas 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?

States a specific verb and resource ('List the Google Ads import jobs set up on the account') and immediately enumerates the returned fields, so the agent knows exactly what comes back. It also draws an explicit boundary against a near-miss interpretation ('Only Google Ads imports are listed, not file imports'), which separates it from any file-import sibling.

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?

Provides a concrete triggering scenario: 'Use it when a campaign changed or was paused and nobody did it,' which is a real diagnostic path an agent can act on. It does not name a specific alternative tool (e.g. msads_get_campaigns or list_google_ads_links) for the case where the agent wants the link config rather than the job list, so it stops short of full when-not guidance.

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