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

Annotations only declare readOnlyHint=false, idempotentHint=false, destructiveHint=false. The description adds substantial behavioral context beyond that: nothing is sent to users, publishing requires a human in the admin panel, the response includes editor_url, and the response carries validation results (errors, warnings). This is exactly the kind of safety-relevant disclosure an agent needs before invoking a write operation.

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 compact sentences, each earning its place: purpose, safety/response behavior, and format/validation guidance. The most decision-relevant fact (nothing is sent to people) is front-loaded, and there is no filler. The second sentence is slightly dense with three clauses, but the overall structure is efficient.

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 tool with a complex nested graph object and no output schema, the description covers the essentials: purpose, the non-distribution guarantee, response contents (editor_url, errors, warnings), and the correction workflow. Delegating the graph structure to get_funnel_format is a reasonable completeness strategy, though it doesn't clarify how the draft is later published or whether it appears in funnel listings.

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 0% and none of the three required parameters (bot_id, name, graph) have descriptions. The description partially compensates by pointing to get_funnel_format for the graph parameter's structure — the most complex parameter — but adds nothing about bot_id or name semantics, leaving the agent to infer them from titles. Partial compensation warrants a 3.

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 states a specific action: creating a new bot funnel as a draft ('Новая воронка бота черновиком'). The draft qualifier distinguishes it from publish/create siblings, and the references to get_funnel_format and editing the draft orient the agent among related tools. However, sibling differentiation is implicit rather than explicit — it never names a tool like update_funnel_draft as the alternative for modifying the draft.

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 conveys when this tool is appropriate: to create a draft with no user-facing impact ('Людям ничего не уходит'), and it routes the agent to get_funnel_format for the graph structure and to 'правкой черновика' (editing the draft) for fixing validation errors. It lacks explicit when-not-to-use statements or a named alternative, so the guidance is clear context rather than full exclusion logic.

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