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

Adds substantial context beyond the annotations: it replaces saved derived state, may record level-change history, may email the owner on standing changes, and cannot set or raise a level by request. This aligns with destructiveHint=true and gives the agent enough warning about side effects.

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 front-loaded, with each sentence adding useful operational context. The dashboard analogy and the explicit side-effect disclosure earn their place.

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 destructive mutation tool with an output schema, this covers the key behavioral risks: saved state replacement, history/email side effects, membership requirement, and the inability to manually raise a level. Nothing important for correct invocation 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 explains focus, level, and business_id semantics. The description does not add further parameter meaning beyond saying it operates on one business, so baseline 3 is appropriate.

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: recompute one business's trust level from live activity and save it. It also distinguishes itself from get_trust_level by noting that it returns the same view plus movement and persists the recomputed state.

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?

Gives clear usage context, especially right after an owner adds a card, and notes the current-business-membership requirement. It does not explicitly frame get_trust_level as the read-only alternative, but the recompute-and-save distinction is clear.

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