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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds the crucial semantics those hints only imply: this is a partial merge ('only the given fields change') and array fields are wholesale-replaced rather than appended. That array-replacement warning is exactly the data-loss behavior an agent needs to avoid clobbering an existing list; what is missing is what happens on empty/null values and any permission requirements.

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?

Two compact parenthetical clauses, zero filler, and the merge semantics are front-loaded immediately after the verb. Every clause carries information the schema does not.

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, idempotent mutation tool with 13 undocumented parameters and no output schema, the description does far too little: it never lists the mutable fields or their expected value shapes, nor whether clearing a field is possible. The merge/array rules are the right core, but the coverage gap on parameters leaves the agent guessing about inputs.

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 0% across 13 parameters, and the description names none of them. The one rule given ('Arrays replace the stored list') is genuinely useful for the five array fields, but it leaves the eight scalar fields (diet, gender, dateOfBirth, smokingStatus, etc.) entirely undefined in both schema and description.

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+resource ('Update the health context') that clearly pairs with the sibling stackwell_get_health_context. It does not enumerate which fields belong to the health context, but an agent can tell update-vs-read apart from the sibling names.

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?

There is no explicit when-to-use guidance, no preconditions mentioned (e.g. that a health context must exist), and no routing advice relative to stackwell_get_health_context or the other stackwell mutation tools. Only the patch-semantics parenthetical hints at intended usage.

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