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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so safety is covered. The description adds genuinely new behavioral context by scoping results to accounts 'this connection can read', signaling that the list is permission-filtered rather than a global directory, and it enumerates the returned fields in lieu of an output schema.

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?

Two sentences, both front-loaded with the useful information: what is listed and what fields come back, then the downstream usage rule. No filler, no repetition of the title.

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 read tool with no output schema, the description carries the return-value burden and does so by naming the fields. Minor gaps remain: ordering of results, behavior on an empty or single-account connection, and whether paging applies.

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 takes zero parameters, so there is nothing to disambiguate and the baseline is 4. The only identifier mentioned (accountId) is explicitly framed as an input to other tools, not to this one, so no confusion is introduced.

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 + resource ('List the Microsoft Advertising accounts') plus the exact fields returned (id, name, account number, currency, time zone, status). It also positions itself against the sibling msads_ tools by explaining that the returned accountId feeds them, so an agent can tell what this tool is for without opening anything else.

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?

The second sentence gives a clear trigger: use the accountId with the other msads_ tools when more than one account exists, which implies calling this first to resolve the account. It stops short of an explicit 'call this before any other msads_ tool' instruction or stating what to do with the result when only one account is returned.

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