account_write_config

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

The description states that write:true 'write[s] detected file-based configs in place', i.e. it mutates files on disk, while the annotations declare readOnlyHint=true and destructiveHint=false. An agent trusting the annotations would assume this tool has no side effects, which is false for the documented write path. This is a direct contradiction (though the description's own safety notes — 'backs up first, never clobbers a malformed file', 'Secrets are never inlined' — are genuinely informative and align with idempotentHint/destructiveHint=false).

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?

Three tight sentences, front-loaded with the purpose ('Register this server with your MCP client') before mode details and safety guarantees. Every clause earns its place: the default behavior, the opt-in write path, and the backup/non-clobber promise.

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 correctly tells the agent what the default return is ('the exact snippet/command to add') and covers the risky write path's guarantees. It omits what happens for undetected/unsupported clients or on write failure, but for a zero-required-parameter helper on a fully documented schema this is nearly 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 the schema already documents name (default mcp-google-multi), write (default false = snippet only) and the client enum with 'default = all detected'. The description repeats the write-mode semantics without adding format, precedence, or resolution details beyond the schema. Baseline 3 is correct when the schema carries the load.

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 states a specific verb and resource: 'Register this server with your MCP client ... returns the exact snippet/command to add.' It is immediately distinguishable from siblings like account_add/account_reauth, which concern accounts rather than client-side config generation. The two operating modes (emit snippet vs. write in place) are named up front.

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 clearly prescribes when to use each mode: default returns the snippet, 'Pass write:true to write detected file-based configs in place.' Concrete client targets (Claude Code / Claude Desktop / Cursor) are given. However, it never routes the agent away from adjacent tools (e.g., account_add) or states prerequisites, so it stops short of the explicit when/when-not/alternatives bar.

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