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

Annotations are sparse (readOnlyHint=false, openWorldHint=false, destructiveHint=false), so the description carries the burden. It discloses important behaviors beyond the schema: server-side filters by category-matched stores, return of choiceSetId/pageUrl/catalogSearchScopeRu, always sharing pageUrl in chat, and not hand-picking SKUs from other stores. This gives the agent a realistic model of what happens when invoking the tool.

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?

The description is long but not padded: each sentence encodes a different operational rule or exclusion. The core purpose and mandatory trigger are front-loaded, and the later sentences cover safety and fallback behaviors. It could be better structured as bullets, but the content earns its place.

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?

Given the tool has no output schema and significant interaction complexity, the description is remarkably complete. It covers the return values, trigger conditions, parameter usage, downstream gating to create_purchase, sessionId retry handling, and forbidden alternatives. An agent has enough context to call the tool correctly and avoid common failure paths.

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 80%, so the baseline is 3. The description adds meaningful parameter semantics beyond the schema: for baskets/recipes pass kind=bundles and wants[{q}] for every ingredient, for apparel pass gendered wants, and pass canRenderImages=false for ChatGPT/Grok. It does not add much beyond the schema for agentIntroRu or sessionId, but the operational specifics it provides are valuable.

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 starts with a specific verb and resource: 'Create a comparison page (choice board, 2–4 options with pros/cons)'. It clearly differentiates the tool from siblings by specifying the trigger condition ('MANDATORY when search_products returns 2+ similar hits') and by describing the exact output artifacts. An agent can identify when this tool, rather than search_products or create_purchase, is needed.

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 exhaustively specified: call immediately on clarifyHint.action=present_choices, do not wait for «сравни», pass kind=bundles with wants for every ingredient, and do not create_purchase until get_choice_status shows chosen. It also gives explicit exclusions such as 'NEVER substitute a markdown table' and 'Never begin_agent_link again'. This is the strongest possible guidance for an agent.

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