meta health check

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

Annotations already declare readOnly, idempotent, and non-destructive, so the safety profile is covered. The description adds genuine context beyond that: it never exposes the access token, unresolved checks stay 'unknown', and granted scopes do not prove app access level or Meta security clearance — a meaningful reliability caveat an agent would not infer from annotations alone.

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 front-loaded sentences, with the read-only diagnostic purpose stated first and the caveats second. Dense but every clause carries signal; the caveat sentence is slightly packed but not padded.

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 structure needn't be explained. For a parameterless diagnostic, the description supplies the only genuinely needed extras — the non-exposure guarantee and the limits of what a passing check proves — leaving nothing an agent must guess.

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 the baseline of 4 applies; there is nothing for the description to disambiguate at the argument level.

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 ('Read-only connection diagnostic') and enumerates exactly what it inspects: token identity, granted permissions, and accessible ad accounts. This cleanly distinguishes it from data-fetching siblings like meta_get_business_assets and from the seeming overlap with meta_debug_token by framing it as a connection health probe.

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 framing as a 'connection diagnostic' implies usage (verify a connection before running other calls), but it never explicitly says when to choose this over meta_debug_token or meta_list_ad_accounts, which overlap functionally. The caveats about unknown checks imply a pre-flight role without stating it.

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