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

Annotations only signal possible mutation (readOnlyHint=false, destructiveHint=true); the description adds the crucial nuance that only SELECT/SHOW run unless allowWrites is set, and that writes require full-access keys. It also discloses the passwordless auth mechanism (sudo -u postgres, unix socket, etc.), that no password is stored, and the CSV/TSV return format — all beyond structured metadata.

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 dense sentences carry the core purpose, auth model, safety default, and engine-specific behavior without fluff. The most important constraints (passwordless, read-only default) are front-loaded, and supporting details are compactly grouped.

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?

With no output schema, the description wisely explains return formatting for SQL engines and gives a concrete MongoDB usage example. It is less explicit about redis-cli output formatting and does not discuss failure modes, but for a multi-engine query tool the coverage is sufficient for correct invocation.

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 input schema already covers 100% of parameters with useful descriptions, so the baseline is 3. The description adds extra semantics for the query parameter (MongoDB shell-expression example, SQL CSV/TSV output) and explains the default read-only behavior tied to allowWrites, which is not fully expressed in the schema itself.

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 ('Run a database query') with a clear resource (a chosen server's database engine) and immediately differentiates itself from generic shell/ssh tools by specifying it operates via each engine's client over the tunnel. The description also enumerates supported engines, so an agent can tell exactly what this tool does.

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?

Explains when to use it (when a database query is needed on a known host) and provides strong selection cues: no DB password needed, local trust, read-only by default, and MongoDB expression mode. It does not explicitly name sibling alternatives like ssh_exec for ad-hoc shell commands or data_tables for schema listing, so exclusion guidance is implicit rather than explicit.

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