mdb_connect

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

With no annotations, the description carries the full burden and does disclose real behavior: it runs a health check, establishes a session that all other mdb_* tools then reuse, and replaces any previous dynamic session (a state-destructive side effect). It does not say what happens on failed auth/timeout or whether credentials persist in memory, which are the remaining gaps for a credential-handling tool.

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?

Four short sentences, front-loaded with the core action and the credential-source constraint, then sequencing, side effects, and the session-reuse rule. Every sentence adds a distinct operational fact with no padding.

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 an 8-parameter connection tool with no output schema, the description covers the essential context: credential source, when to call it, health check on success, and session precedence over prior sessions. It stops short of describing failure behavior or the outcome of readOnly defaults, but the schema already supplies the latter.

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 100%, so the schema documents all eight parameters and the baseline is 3. The description adds genuine meaning beyond the schema by explaining that the database can be omitted on subsequent calls because the session retains it, which is a parameter-interaction detail the schema cannot express.

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 ('Connect to MonetDB') and immediately narrows scope ('with user-provided credentials, NOT from config.json'), which separates it from any config-driven path among the mdb_* siblings. An agent knows exactly what this tool does before 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 an explicit trigger ('Always call this first when the user gives you host/user/password/database directly') plus a when-not ('NOT from config.json'), and adds a follow-on rule for subsequent calls. Nothing about sequencing relative to mdb_disconnect/mdb_health_check is left to inference beyond what is obvious from the names.

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