Delete symptom (erases the entry)

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

Annotations already declare `destructiveHint: true`, `readOnlyHint: false`, and `idempotentHint: false`, so the bar is lower. The description still adds substantial context beyond annotations: the entry is overwritten in the cloud, disappears from `get_symptoms` and the app, and the response carries `deleted_entry` so a mistaken delete can be logged again.

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?

Front-loads the core action and then layers conditions and caveats in a logical order. Every sentence adds useful information, though the description is slightly longer than strictly necessary and the parenthetical '(agent write)' is mildly redundant given annotations.

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 single-entry tool, the description covers purpose, usage, alternatives, side effects, and a key restriction. It omits some edge cases such as auth requirements or behavior for a nonexistent `entry_id`, but an output schema exists and annotations already carry the destructive/idempotency profile.

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?

There is one parameter (`entry_id`) with 0% schema description coverage. The description does not define what `entry_id` is, where to obtain it, or its format; it only mentions `entry_id` incidentally in the `update_symptom` alternative. With low coverage, the description should compensate but does not.

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: 'Erase one reported symptom that was logged by mistake.' It also scopes the tool to erroneous entries and explicitly distinguishes it from `update_symptom` and `log_symptom`, so an agent can route correctly without opening sibling schemas.

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 explicit when-to-use conditions (duplicate, wrong person, symptom they did not have) and an explicit when-not-to-use rule ('A symptom that simply ended is NOT deleted'), naming `update_symptom` as the alternative. It also states a hard limitation: Apple Health imports cannot be deleted here.

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