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

With no annotations provided, the description carries the full behavioral burden and does so well. It discloses exact error behavior (-32012 with blocked_by: key, -32014 with scope: key), the clearing semantics of empty values, and the hard constraint that a key can never exceed account-level settings. This is substantive context beyond the schema.

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 dense but well organized, with the main purpose front-loaded and backtick formatting making parameter semantics scannable. Every sentence adds value: scope, error behavior, constraint, and read-vs-write distinction. No wasted words.

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?

The description is largely complete for a read/update tool: it covers the main parameters, error semantics, scoping, and constraints. The main gap is that `window` is not mentioned in the description and no output schema is present, leaving the read-report behavior slightly underspecified. Still, this is a minor gap given the schema covers `window`.

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 coverage is 100%, so the baseline is 3. The description adds meaning by clarifying that `enabled` is the FULL list to keep on, `caps` applies per key alone, an empty value clears, and id-only means read. However, the `window` parameter is not integrated into the tool description, even though the schema explains it.

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 uses a specific verb pair, 'Read or change', and identifies the exact resource: which gateway services one API key may use and its per-service monthly unit caps. It clearly distinguishes this from account-level siblings by emphasizing 'ONE of the account's API keys' and listing the service types.

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 gives clear usage context: 'No arguments besides id = read' tells the agent how to perform a read, while the descriptions of `enabled` and `caps` imply how to perform changes. It does not explicitly name alternative tools or state when not to use this tool, so it stops short of a 5.

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