check_database

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

With no annotations, the description carries the burden and does real work: it discloses that failures come back as a 'sanitized cause' (no raw credentials/DSNs echoed), that active_port is reported when the answer arrives on a fallback port, and that this acts as a live re-probe for tunneled connections. It stops short of stating whether the probe is read-only or what latency/timeout behavior to expect.

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 short sentences, front-loaded with the core action and the return shape. The fallback-port/re-probe note is slightly terse but earns its place by flagging a non-obvious behavior; nothing is 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?

For a single-optional-parameter probe with an output schema already covering the response shape, the description supplies the action, the scope control, the error-safety behavior, and the tunnel re-probe nuance. Nothing an agent needs to call it correctly is missing.

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 coverage is 0% — the parameter is just an untyped optional 'Database' string with default null. The description compensates by explaining that supplying one targets that database while omitting it checks all, which is exactly the meaning the schema fails to convey.

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 for one database') plus the return contract ('OK or a sanitized cause'). This clearly separates it from siblings like list_databases (enumeration) and doctor (broader diagnostics) without needing either schema opened.

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 phrase 'Test connectivity' implies when to reach for it, and '(or all)' implies the broad sweep case, but there is no explicit when-to-use versus doctor, nor guidance on when a per-database check is preferable to a full sweep. Usage is inferable rather than stated.

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