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

The description substantially enriches the readOnly/idempotent annotations by disclosing exactly what the engine reads (metrics and sensory_tags, not notes), how bean age is computed (at pulled_at using the shot's own bean), and what output context is emitted (bean_context). This is meaningful behavioral information beyond the structured annotations, and there is no contradiction with the declared readOnlyHint, idempotentHint, or destructiveHint.

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 composed of three dense sentences, each earning its place: the first states the core outputs, the second explains bean-resolution semantics and safety, and the third states the key input prerequisite and failure mode. It is front-loaded with the main purpose and contains no filler or redundant restatement.

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 single optional parameter, the presence of an output schema, and readOnly/idempotent annotations, the description covers the essential operational context: what data is used, how bean context is resolved, what must be prepared before calling, and what can go wrong. The only minor omission is an explicit pointer to diagnose_preview, but the description is otherwise complete for safe and correct invocation.

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?

The input schema already documents shot_id as optional with a default of the last pulled shot, so schema coverage is 100%. The description adds meaningful parameter-related context by explaining that diagnosing an older or differently-filed shot is safe because the shot's own bean and pulled_at are used. This goes beyond the schema's basic field documentation and helps the agent reason about the optional shot_id behavior.

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 states a specific verb and resource: 'Evaluate shot metrics to provide ranked hypotheses (C6) and warn on flip-flops (G2) or fatigue (G6).' It clearly describes what diagnose_shot does and distinguishes itself by clarifying it uses the shot's own bean rather than the active profile and reads sensory_tags rather than free-text notes. However, it does not explicitly name or contrast a sibling tool like diagnose_preview, so sibling differentiation is implicit rather than explicit.

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 guidance: taste feedback must be recorded as sensory_tags via log_shot or update_shot before diagnosing, and free-text notes are explicitly not read. This gives the agent a concrete precondition and warns about a common misuse. It does not explicitly state when to prefer an alternative tool such as diagnose_preview, so it stops short of full when/when-not guidance.

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