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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description earns credit by adding two non-obvious traits: it returns metadata rather than credential values, and it produces no credential-access audit event — a meaningful distinction for a security-sensitive tool. It stops short of describing return shape or error conditions.

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?

Three tight sentences, front-loaded with the action and scope, then usage conditions, then behavioral caveats. No restatement of the title and 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 zero-param read tool with full annotation coverage, the description covers purpose, when to call, and what is not returned. The only gap is the actual shape of the returned metadata, which is undocumented since no output schema exists.

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 for the description to disambiguate; baseline 4 applies. The description correctly implies a no-argument call against the connection's own identity.

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 ("Inspect") plus a precisely scoped resource: the authenticated agent's identity and enabled service/method access policies, with an extra note that OAuth connections report approved key names. It is clearly separable from get_credential (this returns metadata, not secrets) and from list_audit_events (this inspects policy, not event history).

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?

Gives two concrete triggering conditions: before credential retrieval, and when troubleshooting access. That implicitly routes the agent away from get_credential for read-only identity checks, though it never names the sibling tools or states exclusions explicitly.

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