ym_get_raw

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is known. The description adds value beyond that: it restricts verbs to GET, HEAD, OPTIONS, explains the return envelope ({"ok": true, "status", "data"} or error), and notes that body is rare but sometimes needed. It does not mention auth or rate limits, but those are likely handled by the service layer. No contradiction with annotations.

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: a one-sentence purpose, a target API reference, safety constraints and sibling pointers, then a clean args list with defaults and examples. It is a bit long but every part earns its place. The most important scoping information (read any endpoint) is front-loaded. No redundant repetition of schema fields.

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 generic raw-read tool, this description is complete. It covers purpose, usage boundaries, all parameter semantics, return format, and error envelope. It even notes the rare body case. With annotations covering read-only and open-world behavior, and an output schema present, nothing essential is missing for an agent to call 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?

Schema description coverage is 0%, so the description must fully explain parameters. It does: path (full path starting with '/', example), method (safe verb, default GET), host (override, default service host), query (query-string params), body (JSON body, rare on reads). All five parameters are given clear semantics with examples, fully compensating for the lack of schema descriptions.

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?

States a specific verb (read) and resource (ANY endpoint by path), explicitly covering endpoints missing from the catalog. It clearly distinguishes from ym_write_raw and ym_delete_raw, which are mentioned as alternatives for data changes. This makes its purpose unmistakable and differentiates it from the many sibling tools.

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?

Explicitly tells when to use this tool (read-only raw access to any endpoint) and when not to (use ym_write_raw for changes, ym_delete_raw for deletions). It also implies use for endpoints not covered by catalog-specific tools, and provides the target API documentation link. This is strong guidance on selection among alternatives.

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