connection_status

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, but the description adds semantics annotations cannot express: the tool performs no network I/O or file writes, auth_status stays unknown from a cached token, and live_access is always not_checked even after a prior successful data call. That last point is a genuinely counterintuitive behavior that would otherwise cause an agent to misread the result.

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 short lines with no filler; the scope constraint is front-loaded before the caveats and the alternative pointer. The prose is slightly fragmented into declarative fragments, but every line carries distinct information rather than restating the name.

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?

An output schema exists, so return-value explanation is rightly omitted; the description instead covers what the check does and does not prove, which is the gap that matters for a status tool. The only remaining hole is the undocumented `account` argument, which keeps it from being fully complete for a tool that takes an input parameter.

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 0% for the single optional `account` parameter, so the description carries the burden of explaining what an account selector means here (and what the default of null resolves to). It says nothing about the parameter at all, leaving the agent to guess whether omitting it checks all accounts or a default one.

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 scope: 'Inspect local setup only', followed by an explicit exclusion list (no browser, token refresh, API call, file writes). This distinguishes it from the live-verification siblings. It stops short of naming exactly what 'local setup' comprises (config file presence, cached credential, env vars), which is inferable from the name but not stated.

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 routes the agent: 'Use list_properties and get_property separately to verify actual Google access' is a named alternative with the condition that selects it. It also states the negative case, that a cached token cannot prove validity, so an agent knows not to treat a positive result as proof of access.

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