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

Goes well beyond the annotations: it names the concrete external systems (Pohoda, ABRA Flexi) behind openWorldHint, confirms the idempotent no-double-send behavior declared by idempotentHint, and adds a side effect not in the annotations — the action is recorded in the document history. That is exactly the added context this dimension rewards.

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?

Front-loads the core action, then layers default behavior, the opt-in flag, idempotency, and audit logging in short, purposeful sentences. Dense but every clause carries information; only marginal room to tighten.

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 full annotation coverage and no output schema, the description covers defaults, external side effects, idempotency, and history logging. Remaining gaps are minor: whether approval is reversible, required permissions, and the resulting document state are not stated.

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 baseline is 3; the description still adds meaning by clarifying that sendToAccounting defaults to non-accounting approval and that an already-forwarded document will not be forwarded again. It does not elaborate on comment or companyId, but those are already fully documented in the schema.

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 ("Schvali doklad") and immediately qualifies the two distinct approval modes (local-only vs. forwarding to accounting). This is unmistakably different from the sibling reject_document / bulk_reject_documents tools without needing to open any schema.

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?

Gives clear operational context: the default invocation is approval only, and the accounting forward is strictly opt-in via sendToAccounting. It does not explicitly name alternatives (e.g., when to reject instead) or state prerequisites/permissions, so it stops short of full when/when-not guidance.

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