Test site connection

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

Annotations already carry the safety profile (readOnlyHint=true, destructiveHint=false), and the description adds concretely what the tool checks and reports, plus that it verifies the optional companion plugin — useful behavioral context. However, it does not disclose side effects for a non-idempotent, openWorld tool: the outbound network call, latency, or any transient state it might leave. IdempotentHint=false with openWorldHint=true suggests an external side-effecting operation that the description leaves unexplained. No contradiction with annotations.

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 with zero waste. The first enumerates the tool's scope and outputs in compact clause form; the second delivers the usage directive. The core diagnostic message is front-loaded before the guidance, and every word earns its 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?

For a simple tool (zero required params, no output schema), the description thoroughly explains return semantics by listing exactly what will be reported. The only gap is that, given openWorldHint=true and idempotentHint=false, an agent might be warned about network latency or non-idempotency implications. Minor for a diagnostic tool whose output semantics are already well covered.

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 only parameter, site_id, has 100% schema description coverage that already explains the optional behavior, defaulting logic, and a pointer to list_sites for valid ids. The description adds no parameter-level detail beyond what the schema provides, so the baseline 3 is appropriate — schema does the heavy lifting and nothing is lost.

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 — 'Test connectivity and authentication against a site' — and enumerates exactly what it reports: REST reachability, credential authentication, user mapping, roles/capabilities, and companion-plugin presence. This distinguishes it sharply from diagnostic siblings like get_audit_log, run_ability, or audit_content; an agent can tell what it does without opening the schema.

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 explicit when-to-use guidance: 'Run this first when anything is behaving strangely — it names the specific misconfiguration rather than a generic failure.' This positions it as the initial diagnostic step. It does not name explicit when-not-to-use conditions or alternatives that would supersede it, so it stops one step short of fully excluding sibling tools, though the schema's list_sites reference helps disambiguate parameter sourcing.

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