ozon_call_raw

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

The description adds significant behavioral context beyond annotations: it maps HTTP verbs to safety levels (GET=read, POST/PUT/PATCH=write, DELETE=destructive) and mentions confirmation rules. It also discloses the return format ('Returns JSON: {"ok": true, "status", "data"} or the error envelope'). Annotations already indicate destructiveHint=true and readOnlyHint=false, so the description enriches rather than contradicts them.

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 front-loaded with the core purpose and uses a clear bulleted list for parameters. It is efficient with no fluff, but the placeholder '{svc}_call_method' is vague and slightly confusing. The mention of two confirmation parameters could be consolidated, but overall it is well-structured and readable.

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 raw, unrestricted nature and the presence of an output schema, the description covers the essential aspects: purpose, safety inference, parameter semantics, and return format. It omits details like authentication requirements or rate limits, but these are likely common to the service and may be handled elsewhere. The description is sufficient for an agent to correctly invoke the tool for arbitrary endpoints.

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 0%, so the description must compensate, and it does: every parameter is listed with a brief explanation (method, path, host, query, body, confirm_write, i_understand_this_modifies_data). It provides a concrete path example and explains defaults for host. However, it does not clarify the relationship between confirm_write and i_understand_this_modifies_data, and query/body formats could be more detailed.

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 clearly states the tool's function: 'Execute ANY endpoint, even ones not in the catalog (full API coverage).' It uses a specific verb ('Execute') and resource ('endpoint'), and explicitly contrasts with catalog tools by mentioning 'even ones not in the catalog,' distinguishing it from sibling tools like ozon_call_method. The name 'ozon_call_raw' also reinforces the raw, unrestricted nature.

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 implies usage for endpoints outside the catalog ('even ones not in the catalog') and references confirmation rules via 'Same confirmation rules as {svc}_call_method,' but it does not explicitly say 'use this instead of call_method for uncatalogued endpoints.' It provides clear guidance on safety based on HTTP verb, which helps the agent decide when confirmations are needed, but it could be more explicit about the alternative tool.

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