manage_runtime_db

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety profile is covered externally. The description adds the return categories (diagnostics, audit trees, snapshot metadata, diff reports), which is useful since there is no output schema, but it never says which of the six actions is the destructive one or that restore overwrites the current database — the most important behavioral fact is left implicit.

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, capabilities front-loaded and the routing hint second; nothing is padding. The middle clause enumerating six action names is somewhat redundant with the schema enum, keeping it from a 5.

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 six-mode tool with no output schema, the description gives only a one-line summary of possible returns and no per-action behavioral detail. An agent knows the tool's domain and the get_metrics alternative but not how the actions differ in effect or which parameters each consumes, so it is minimally adequate rather than complete.

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 description coverage is 100% and the action enum is fully documented in the schema, so the baseline of 3 applies. The description repeats the action names but adds no mapping of which parameters are required for which action (e.g., that 'name' matters only for snapshot/restore/diff), which is the genuinely missing information.

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?

The description names a concrete resource (runtime database) and enumerates the six operations it bundles (stats, audit, doctor, snapshot, diff, restore). It also distinguishes itself from the sibling get_metrics, so an agent can route between the two without opening schemas. It stops short of a 5 only because the six actions are listed rather than individually characterized.

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?

It gives an explicit selection rule against a named alternative: use this instead of get_metrics when auditing SQLite integrity/Merkle proofs or restoring snapshots. That is clear context plus an alternative, but it offers no when-not guidance (e.g., that read-only diagnostic needs should prefer a lighter tool) and no prerequisites such as required permissions for restore.

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