sbis_fetch_all

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

Annotations declare readOnlyHint=true, and the description aligns by calling it a 'read endpoint.' It adds value beyond annotations by explaining the pagination mechanism, the automatic path detection, the max_items hard cap to protect context, and the exact return JSON structure including the 'truncated' flag. It could mention potential errors or rate limits, but for a read operation this is adequate.

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 well-structured: the opening sentence states the core purpose, followed by a brief note on pagination styles, then a clean Args list, and finally the return format. Every sentence earns its place, and the most important information (auto-pagination) is front-loaded. It is detailed but not verbose.

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's complexity (multiple pagination styles, parameter overrides, and a safety cap), the description covers all essential aspects: what it does, how it handles pagination, what each parameter does, and the return shape. The output schema is mentioned, which offloads return structure details. No critical information is missing for an agent to invoke it correctly.

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?

Despite 0% schema description coverage, the description's 'Args' section explains every parameter: operation_id (read endpoint from catalog), query/body/path_values (base params, cursor fields managed), items_path (override), limit (page size), max_items (hard cap). This fully compensates for the schema gap and adds critical meaning, such as the default of 10000 for max_items and the automatic management of cursor fields.

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: 'Auto-paginate a read endpoint and return every row in one response.' It clearly distinguishes itself from siblings like sbis_get_raw (which fetches a single page) and sbis_call_method (generic call) by emphasizing the auto-pagination and aggregation behavior.

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?

It explicitly states the pagination styles it handles (offset, last_id, cursor, page, lastChangeDate), which implies it should be used for endpoints that use any of these styles. It also mentions that cursor fields are managed automatically, indicating the tool is designed for bulk retrieval. However, it does not explicitly name alternatives or state when NOT to use it, leaving some inference to the agent.

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