prune_store

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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=false, but the description adds material context beyond them: the operation is local-only, nothing is removed from Signal itself, it is irreversible locally, and it cascades into attachment records and search index entries. It also discloses the return shape {deleted, older_than_days}, which the absence of an output schema makes valuable.

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 text is a single dense paragraph that front-loads the core action before moving to parameter semantics, return value, and sibling routing. It is slightly long and the parameter sentence partially restates the schema default, but no sentence is wasted.

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 one-parameter destructive tool with no output schema, the description covers the action, its cascade effects, irreversibility, local-only scope, parameter semantics, return shape, and alternatives. An agent has everything needed to call it correctly or choose a sibling instead.

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 baseline is 3, but the description adds the positivity constraint ("must be positive") and the precise comparison semantics (timestamp older than now minus N days) that the schema's one-line description does not spell out. That is a modest but real increment over the structured field.

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 states a precise verb (delete) plus resource (locally stored messages older than N days) and explicitly scopes it to signal-mcp's database, including the cascading deletion of attachment records and search index entries. It also names the siblings it is not (delete_local_messages, clear_local_store), so an agent can distinguish it immediately.

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 when-to-use ("keep the store small") and routes the agent to two named alternatives with their distinguishing conditions: delete_local_messages for one conversation, clear_local_store to wipe everything. Nothing is left to inference.

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