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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the mutation safety profile is covered. The description adds real value beyond that: the created invoice waits for approval in the DokladBot dashboard and is never auto-sent to the customer, which is exactly the behavioral context an agent needs.

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?

Two tight sentences with zero waste; the critical constraint (draft, not sent) is front-loaded in the second sentence.

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 mutation tool with no output schema and 44% param coverage, the approval-workflow disclosure covers the most important gap but leaves return value (e.g., draft identifier) and several parameters unexplained.

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 only 44% across 9 parameters, and the description mentions no parameter at all. Parameters like buyerDic, buyerIco, buyerAddress, and note are undocumented in both places, so the description does not compensate for the coverage gap.

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?

States a specific verb and resource (creates a draft of an issued invoice) and emphasizes 'NAVRH' so the agent knows no finalized invoice is produced. It does not explicitly name any sibling it contrasts with, but the sibling set is almost entirely read/list tools, so the operation is easily distinguishable.

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?

Usage is only implied: the draft-then-approve framing tells the agent this is the entry point for issuing an invoice, but there is no explicit when-to-use, no prerequisites (e.g., which company/credentials), and no mention of alternatives such as generate_vat_filing.

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