backup_create

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

Annotations already declare this as a non-read-only, non-destructive, non-idempotent write, so the bar is lower, yet the description still adds real value: asynchronous processing, the full data scope (invoices, clients, products, settings), and the job-ID return contract. It omits what happens to previous backups or any retention/overwrite behavior, which for a non-idempotent create would be the remaining useful detail.

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?

Three short sentences, front-loaded with the action, then scope, then return contract. Nothing is repeated and nothing extraneous is included.

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 correctly states what is returned (a job ID) and that processing is async, which is the key agent-facing fact. Minor gaps remain around retention, permissions, and interaction with existing backups, but nothing blocks a correct call.

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 both parameters are already documented; the description adds only the framing that files are optional, and its word "Optionally" is slightly at odds with the schema's default of true. It also describes the target as "the active company" without acknowledging the companyId override.

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 opens with a specific verb and resource ("Create a new backup job") and scopes it to the active company, with a parenthetical listing exactly what data is captured. It doesn't explicitly name the sibling tools (backup_status, backup_restore, backup_history), but the create semantics are unambiguous against them.

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 line "Returns a job ID to check status" implies that backup_status is the follow-up tool, but the description never states when to create a backup versus when to use a restore or history tool, nor any prerequisites. Usage is inferable rather than stated.

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