backup_create

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

No annotations are provided, so the description carries the full behavioral burden. It discloses that processing is asynchronous and returns a job ID, which is valuable. It also notes what's included (all company data plus optional files). However, it doesn't disclose whether this mutates state beyond creating a job, whether it can be called repeatedly (duplicate backups), cost implications, or what the backup download/restore flow entails. For a create-type tool with zero annotations, more disclosure of side effects would help.

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 sentences, zero filler. It front-loads the core purpose, then covers scope, optional behavior, and return value efficiently. Every sentence adds information relevant to decision-making and invocation.

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 create-tool with 2 documented params and no output schema, the description is reasonably complete: it covers what happens (async job), what's included, the optional flag, and the return value. It doesn't explain how to retrieve the backup or interpret the job ID beyond 'check status,' but sibling backup_status and backup_download tools exist to cover those. Given the tool's simplicity and full schema coverage, this is solid.

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% and both parameters are documented in the schema. The description confirms companyId defaults to active company and includeFiles defaults to true, slightly reinforcing the schema. However, it adds minimal value beyond the schema's parameter descriptions. Baseline 3 is appropriate given full schema coverage, though the description does reinforce the default behaviors which adds a small amount of semantic clarity.

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 verb+resource: 'Create a new backup job for the active company.' It specifies scope (all company data: invoices, clients, products, settings) and distinguishes from sibling tools like backup_status, backup_download, backup_restore which handle other backup lifecycle stages. This effectively disambiguates it from the 8 backup-related siblings.

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 states it creates a job and returns a job ID to check status, implying the agent should use backup_status to track progress. It mentions the optional includeFiles flag. However, it doesn't explicitly note when to use another tool instead or any prerequisites (e.g., active company must exist). The asynchronous nature is disclosed, which guides the agent on follow-up actions, but no explicit exclusions or alternatives are named.

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