Remember meal

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

Annotations indicate the tool is mutable but not destructive and is idempotent. The description adds that saves are 'local', which is helpful context. However, it does not disclose whether saving a shortcut overwrites existing ones with the same label, or what the response contains. Given the annotations already cover idempotency, the description adds moderate value without contradiction.

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 an example, which is concise and front-loads the purpose. However, it lacks structured elements like bullet points or usage tips, but remains efficient for a simple tool. 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 tool has 8 parameters (2 required) and no output schema, the description is minimal. It does not explain post-save effects, retrieval via 'nourish_list_memory', or error handling. Sibling tools like 'nourish_list_memory' and 'nourish_forget_memory' exist but are not referenced for completeness. More context would improve agent decision-making.

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 description coverage is low (38%). The description only illustrates the mapping of 'label' to 'meal_text' via an example, ignoring other parameters like 'aliases', 'default_meal_type', 'notes', 'tags', and 'response_format'. Critical parameters like 'explicit_user_intent' are described in the schema but not reinforced in the description. The description fails to compensate for the low schema coverage.

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 action ('Save a personal meal shortcut locally') and the resource ('meal shortcut'), with a concrete example ('meu cafe normal' -> '2 ovos e banana'). It distinguishes from siblings like 'nourish_estimate_meal' (which estimates without saving) and 'nourish_forget_memory' (which removes shortcuts).

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 specifies 'after explicit user intent' and the input schema includes an 'explicit_user_intent' boolean, but it does not explicitly state when to avoid using this tool (e.g., when the user just wants a one-off meal log) or mention alternatives like 'nourish_estimate_meal' for estimation or 'nourish_log_intake' for direct logging. The example helps, but guidance is implicit.

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