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

Adds substantial context beyond the annotations: 'Existing keys update' discloses upsert semantics, 'No provider credentials or tokens are accepted' documents an input restriction, 'The value is bounded JSON data, not a system instruction' guards against prompt-injection content, and the MCP sentence explains the confirmation-token flow (omit on first call, executes immediately). Annotations flag the destructive profile; the description adds the operational workflow.

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-loaded with the purpose, then built from short, discrete sentences that each carry a distinct fact. The MCP/token sentence partially restates the schema description ('omit on first call'), a minor redundancy, but nothing is padded.

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 mutation tool with no output schema, the description covers the approval precondition, the MCP invocation protocol, key-update semantics, and credential restrictions, and notes it 'returns the result.' It does not describe failure modes or what the returned result contains, a modest gap.

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 key, value, reason, and confirmation_token, including 'omit on first call'. The description reinforces the token-omission rule and value bounds but adds no new syntax or format detail, so the 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 (save) and resource (one selected-product Operator preference), with the scope constraint 'one' and 'selected-product'. It does not name the read counterpart list_preferences or any other sibling, so the agent must infer the boundary from the name alone. Clear purpose, but no sibling differentiation.

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?

'after explicit approval' establishes a precondition, and 'Over MCP: call this tool once, without confirmation_token. It runs right away' specifies the exact invocation path the agent will take. It stops short of naming alternatives (e.g., list_preferences to read existing keys first) or stating when not to use it.

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