Запрос к Elba Public API

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

No annotations are provided, so the description carries the full behavioral burden. It does disclose real behavior: the tool refuses to execute method/path combinations not allowed by the OpenAPI schema, and mutation calls require prior schema review — genuinely useful context beyond the title. However, it's silent on auth requirements, error behavior when validation fails, response format, and it never warns that DELETE/PUT/POST have destructive side effects. For an unannotated tool that can mutate, this is a partial disclosure.

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, each carrying distinct information: the first states the core behavioral constraint (schema-gated execution), the second gives actionable pre-requisite guidance for mutating calls. No repetition of the title, no filler, and the most important fact is front-loaded.

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?

With no annotations and no output schema, the description bears full responsibility for completeness. It covers the two most critical aspects — the validation gate that prevents invalid calls, and the describe-first workflow for mutations. But it leaves out what an agent needs at runtime: response/return format, error and status semantics, authentication prerequisites, and an explicit warning about irreversibile destructive operations. For a generic executor with destructive potential, the agent is left to guess on operational behavior.

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 75%: method has a self-describing enum, path has pattern plus a concrete example ('/v1/organizations/{id}/bills'), while body and query have only tautological descriptions ('JSON-тело запроса', 'Query-параметры'). The description adds genuine inter-parameter meaning — method and path must jointly form an allowed operation in the OpenAPI schema, so arbitrary combinations will be rejected. It doesn't elaborate body/query semantics, which is acceptable since those are operation-specific and discoverable via elba_describe_operation.

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: 'Выполняет операцию, только если сочетание метода и пути разрешено встроенной OpenAPI-схемой' — a generic request executor gated by the built-in OpenAPI schema. This is a clear verb+resource pairing that distinguishes it from the introspective sibling tools (elba_list_operations, elba_describe_operation), which discover rather than execute. It doesn't explicitly contrast itself against siblings, but the execution role plus schema gate makes the purpose unambiguous.

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 second sentence gives explicit when-to-use guidance: 'Для изменяющих операций сначало изучите схему через elba_describe_operation' — naming the exact sibling tool for the mutating case. The rules imply GET-level calls can proceed directly and the tool enforces schema permissibility. It doesn't cover when to use elba_list_organizations or elba_list_operations, but the relevance routing for the riskiest case is explicit.

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