SQLite Project Memory MCP

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

No annotations are provided, so the description carries the full burden. It mentions 'prune' (implying destructive deletion) and 'dry_run' (from the schema), but doesn't disclose critical behavioral traits: whether pruning is irreversible, what permissions are required, how 'entity and type' grouping works, or potential rate limits. The description adds minimal context beyond the basic action.

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?

The description is a single, efficient sentence that front-loads the core action ('prune older reasoning/log content') and key constraint. There is zero wasted verbiage, making it easy to parse quickly.

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?

Given the complexity (a destructive pruning operation with 4 parameters), no annotations, and an output schema (which might cover return values), the description is incomplete. It lacks essential details: behavioral risks, parameter semantics, and usage context. For a tool that could delete data, this is a significant gap.

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 0%, so the description must compensate for all parameters. It only vaguely references 'entity and type' (hinting at 'entity_id' and 'content_types') and 'most recent records' (hinting at 'keep_latest'), but doesn't explain parameter meanings, defaults, or interactions (e.g., how 'dry_run' affects execution). With 4 undocumented parameters, this is inadequate.

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 clearly states the action ('prune older reasoning/log content') and the resource affected, with a specific constraint ('keeping the most recent records per entity and type'). It distinguishes itself from siblings like 'delete_entity' or 'archive_entity' by focusing on retention pruning rather than full deletion or archiving. However, it doesn't explicitly differentiate from all siblings (e.g., 'apply_performance_tuning' might overlap in purpose).

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 description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, timing considerations (e.g., during cleanup cycles), or compare to siblings like 'archive_entity' for long-term storage or 'delete_entity' for complete removal. Usage is implied through the action but lacks explicit context.

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