Nourish profile update

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

Annotations already indicate idempotentHint=true and destructiveHint=false. The description adds that it rejects sensitive fields, but does not elaborate on idempotency or consequences of rejection. No contradiction with annotations.

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 a single sentence with three crucial clauses: purpose, requirement, and constraint. It is front-loaded with the action and immediately provides key usage conditions, with 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?

Given the complexity of a nested patch object and no output schema, the description provides the essential purpose, a required flag, and a security rule. It does not describe return values or error handling, but annotations and schema partially fill gaps.

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 description adds a meaningful constraint: rejection of secret fields in the patch object, which is not present in the schema's parameter descriptions. Schema coverage is 67%, but the description compensates with this security context. It also reinforces the explicit_user_intent requirement stated in the schema.

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 specifies 'Persist a partial patch to the shared Delx Wellness profile', which is a specific verb+resource combination. It clearly states the tool updates the wellness profile, distinguishing it from read-only tools like nourish_profile_get.

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 explicitly requires 'explicit_user_intent: true' as a condition for use, telling the agent when to invoke it. It also warns about rejected fields (secrets), guiding proper usage, though it does not compare against sibling update tools like nourish_set_goals.

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