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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds value by detailing the exact structure of the returned object and noting that some fields are read-only facts, which helps the agent interpret data correctly. It does not mention any side effects or pagination, but for a settings getter with a small payload, this is sufficient.

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 sentences with no wasted words. The first sentence states purpose and enumerates content, the second gives usage guidance, and the third covers the parameter condition. The most critical information (purpose and usage) is front-loaded, and the grouping list is dense but useful.

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?

Given the tool's complexity (a settings object with multiple nested groups), the description provides a complete enumeration of fields, making it self-sufficient for an agent to know what to expect. It also provides the necessary usage context (before updates) and parameter condition (multiple websites). With an output schema present, the description does not need to explain return format, and nothing essential is 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 100%, and the schema already states 'Website id from get_account. Optional when the account has a single website.' The description repeats this ('Pass website_id when the account has several websites') without adding new semantics. Since the schema fully documents the parameter, the description earns the baseline 3 without extra credit.

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 opens with a specific verb and resource: 'Returns the website's configuration grouped as it appears in the app.' It then enumerates all configuration groups (info, general, content, images, competitors) with their key fields, making the tool's purpose unmistakable. It also implicitly distinguishes itself from the update_* siblings by instructing to read it before updates.

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 states when to use the tool: 'Read it before calling an update_* tool so you only change what the user asked for.' This is a clear directive that positions the tool as a prerequisite for any mutation. It also gives conditional guidance for the parameter: 'Pass website_id when the account has several websites (see get_account),' referencing the correct sibling for context.

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