Произвольная выгрузка

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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds meaningful context by explicitly banning write methods and clarifying that the connector only reads. This goes beyond the annotations without contradicting them; no error or rate-limit behavior is discussed, but that is acceptable for a generic endpoint.

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?

Two sentences with no filler. The purpose is front-loaded, and the constraint about forbidden write methods is placed immediately after the purpose, so an agent gets the critical information quickly.

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 deliberately generic tool with no output schema, the description is sufficiently complete: it explains when to use it, what endpoints are allowed, and references the body, path, and entity parameters through the schema. The lack of return-value documentation is mitigated by the entity parameter that identifies the response root key.

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 description coverage is 75%, and the schema itself documents path with an example, body with the filial_code substitution note, and entity with its fallback behavior. The tool-level description adds no parameter detail of its own, and the 'limit' parameter remains undocumented. This matches the baseline for high coverage where the schema carries the load.

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 opens with a specific verb-resource pair: 'Прямой вызов любого метода $export' (direct call of any $export method). It clearly positions the tool as a generic fallback for when ready-made tools are insufficient, which distinguishes it from all specialized siblings without ambiguity.

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 when to use the tool: 'когда готового инструмента не хватает' (when a ready-made tool is not enough). It also gives a clear exclusion, prohibiting write methods like $import, $change_status, and $attach_data. It does not enumerate specific sibling tool names, but for a generic fallback the reference to 'ready-made tools' is sufficient.

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