Make an outbound HTTP request from the client (sUNC request)

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

Annotations only declare the safety envelope (destructive, open-world, non-idempotent); the description adds substantial behavior beyond that: the ~100 KB response body cap, the internal fallback order, the type-guard/pcall wrapping, and both failure shapes ('request is not available in this executor.' vs transport {error}) and the success shape. This is exactly the extra context annotations cannot carry.

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?

Front-loads the essential capability and executor details in the first quoted sentence, then layers operational metadata. It is dense and mostly earns its length, though the trailing boilerplate ('On failure: inspect tool-schema...') and the Phase/cost/idempotency line read as generic metadata rather than tool-specific value.

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 output schema, the description usefully inlines the return shape ({statusCode, success, headers, body, statusMessage} or {error}) and covers error and fallback paths. It stops short of mentioning rate limits, header restrictions, or timeout defaults beyond what the schema says, but for a 6-param network tool with full annotation coverage this is close to complete.

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 100%, so all six parameters (url, method, headers, body, threadContext, timeoutMs) are already documented with defaults and enum values. The signature line in the description restates them without adding format, constraint, or interaction semantics, so baseline 3 applies.

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 and resource ('SENDS A REAL OUTBOUND HTTP REQUEST from the Roblox client') and immediately names the mechanism and fallback chain (request -> http_request -> syn.request). This distinguishes it cleanly from siblings like ws-connect or scan-network-endpoints, which are different I/O surfaces.

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 draws a contrast with Roblox's HttpService (arbitrary hosts, custom headers) and lists prerequisites ('Requires: active-client, explicit-mutation-approval'), which implies when it is legal to call. However, it names no sibling alternative and gives no explicit when-to-use / when-not-to-use routing, so guidance remains implied rather than stated.

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