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

Annotations claim readOnlyHint=true and destructiveHint=false, but the description explicitly says 'MUTATES' and 'sets current value to 0', which contradicts those annotations. The description is transparent about the mutation, but the contradiction with annotations is a serious issue. However, the description adds behavior context beyond annotations: rebuilds life_state, requires auth, share tokens cannot write, and cost ($0.10). I flag the contradiction and score low due to the conflict.

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 two sentences with high information density. Key action and scope are front-loaded. Each piece adds value: purpose, selection criteria, optional parameters, side effects, auth requirements, and constraints. 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 complete for a complex mutation: it explains side effects (rebuilds life_state), auth requirements, token restrictions, cost, and parameter usage. Despite zero required parameters, it provides all necessary context. The presence of an output schema covers return details, so the description doesn't need to explain that.

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 schema documents all parameters. The description adds value by clarifying the usage of tracker_id vs tracker_title ('prefer tracker_id from get_trackers, or tracker_title fuzzy match'), and mentions reset_at and note semantics. It also hints at idempotency via request_id. This goes beyond schema basics, though parameters are fully described in schema, so a 4 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?

The description clearly states the tool's purpose: it mutates a sobriety/streak tracker by setting value to 0 and restarting the clock. This distinguishes it from sibling tools like get_trackers (read-only) and update_event (generic mutation), though it doesn't explicitly name siblings. The verb 'MUTATES' is explicit and the resource (tracker) is identified. It is concise and unambiguous.

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 provides explicit usage guidance: it tells the agent to prefer tracker_id from get_trackers or use tracker_title as a fallback. It also clarifies required authentication (API key or OAuth with scope context) and warns that share tokens cannot write. This directly aids selection and invocation.

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