create_backup

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

No annotations provided, so the description carries full burden. It richly discloses concurrency safety via SQLite online backup API, integrity verification with PRAGMA integrity_check, deletion of bad backups and raising on failure, indefinite retention (not touched by auto-retention), and the restore_hint in the response. This is exemplary behavioral disclosure beyond any structured field.

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?

Well-organized multi-paragraph structure covering safety, retention, restore, and args. Every sentence adds distinct value. Slightly longer than strictly necessary, but the density of useful information justifies the length.

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 tool with one optional param, an output schema, and considerable behavioral nuance (concurrency, integrity, retention, restore), the description covers all relevant aspects well. It could mention any permission/auth requirements, but nothing suggests those exist. Complete enough for confident 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?

Schema coverage is 0% (the label param isn't documented in the schema descriptions), and the description compensates by explaining the label is a free-text optional label, sanitized to [A-Za-z0-9_-], appended to the filename, with concrete examples. It fully documents the only parameter. Baseline would be 3 but coverage is 0%, so it climbs for compensating.

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?

Description states a specific verb+resource ('Create an on-demand backup of the GnuCash book') and differentiates from siblings like list_backups and prune_backups by focusing on the creation/on-demand aspect. The purpose is immediately clear and distinct from the many other tools.

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 clearly explains when to use this tool (on-demand/manual backup) and explicitly distinguishes it from automatic retention stages. It even mentions the sibling prune_backups and restore is a human action not an MCP tool. However, it doesn't explicitly state 'use X instead when...' for common alternatives since no other create-backup sibling exists.

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