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

Annotations declare destructiveHint=true and readOnlyHint=false, and the description supplies the critical nuance that the call itself writes nothing and only returns status='confirmation_required' with an action_id and plan_token. It further discloses the observable side effect (card becomes «Вирішено» with one journal entry, marked as made via MCP) and the refusal condition, which annotations cannot convey.

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-loaded with the action and the input choice, with the confirmation protocol last where an agent will look for it before calling. It is dense and slightly long — the CONFIRMATION block partially repeats the earlier "the call itself changes NOTHING" sentence — but no sentence is expendable.

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 4-parameter write-path tool with no output schema, the definition covers invocation modes, permission, refusal behavior, side effects, and the confirm_action handoff. An agent has everything needed to call it correctly and to anticipate the confirmation response.

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 the baseline is 3; the description earns above that by adding the oneOf constraint between 'option' and 'text' that the JSON schema does not enforce, plus a concrete example label for 'option'. The remaining value is mostly restatement of the schema's own field descriptions ('the owner's comment').

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+resource ("Answer one Decision Center card") and immediately anchors the id to its source tool (decision_cards_list). It also distinguishes itself from confirm_action by declaring the two-phase confirmation protocol, so an agent can tell the two apart without opening either 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?

Explicitly enumerates the mutually exclusive input modes ("exactly ONE of: 'option' ... or 'text'"), places 'note' relative to 'option', and names an exclusion (a card already resolved or closed is refused). It names the required alternative step (confirm_action) and the prerequisite caller (cabinet owner only).

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