Ozon Self-check

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

Even with readOnlyHint, idempotentHint, and openWorldHint annotations present, the description adds substantial behavioral detail: exact tri-state semantics, what counts as inconclusive vs drift, handling of Cloudflare 403 / CDP-down / non-200 / non-JSON, and the error contract. It also clarifies that inconclusive and drift_detected are valid normal responses, not errors.

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 longer than average but every section earns its place: purpose, tri-state rules, return format, and error semantics are all behaviorally relevant. The main purpose is front-loaded and the structured headings make the detailed tri-state and error contracts easy to scan.

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 zero-parameter self-check tool with an output schema and read-only/idempotent annotations, the description covers everything an agent needs: what it checks, what each verdict means, how transport failures are classified, and when an error is actually raised. No critical gap remains.

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?

The tool has zero parameters and schema coverage is 100%, so there is no parameter meaning to add. The description incidentally clarifies that the tool fetches live data and runs internal subchecks, which is useful context beyond the empty input schema.

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 identifies the tool as a structural drift canary for Ozon with a tri-state outcome, naming the specific resources checked (live search, card, reviews, non-default reviews sort). It distinguishes itself from sibling review/search tools by emphasizing the canary's role in detecting vanished widgets before parsers break.

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 explains that this tool is a pre-emptive drift check rather than a data-fetching tool, and even notes that the reviews_sort subcheck exercises the path on which ozon_reviews pagination depends. It doesn't explicitly list alternative tools to use instead, but the purpose and positioning against siblings are clear enough.

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