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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: in-Worker execution with no upstream HTTP, 1-credit cost charged by mcp-credit-gateway before forwarding, rate limiting, a required sk_live_ key, in-memory-only processing with no storage, and an explicit warning not to submit secrets. That is exactly the operational and privacy context an agent needs before sending user text.

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 critical constraints (required params, modes, cost, privacy) are front-loaded, which is good. But the eight-mode list is enumerated twice — once after `mode` and again in the "Modes:" sentence — and the closing Chinese sentence partly restates the English privacy/rate-limit notes, so real content is diluted by repetition.

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 two-parameter transformation tool with no output schema, the description supplies the return shape ({ text, mode, result }), cost model, auth requirement, rate-limit behavior, and privacy posture. Nothing an agent needs in order to call it safely and correctly appears to be missing.

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 carries the burden, and it does: it states the 8000-character ceiling for `text` and explains each mode's behavior (morse/binary map only convertible characters and keep the rest with an optional skipped note, old_english = Fraktur Unicode, fancy = Math Sans-Serif Bold). Only `reverse` and `title` casing rules are left unstated, a minor gap given how self-evident they are.

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 ("Transform text") and immediately enumerates the eight modes, which separates it cleanly from siblings like translate_text, count_text, and detect_language without opening a schema. It also names the execution model ("pure in-Worker algorithm"), so an agent knows exactly what class of operation this is.

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?

Usage is implied by the mode list — an agent can infer this is the tool for stylizing text rather than translating or counting it — and the "no upstream HTTP" note hints it is the cheap local option. However, there is no explicit when-to-use/when-not statement and no named alternative for cases like translation or character counting.

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