mfp_remove_food_from_diary

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

Annotations already mark this as destructive, and the description reinforces that with 'Remove (delete)'. It adds valuable behavioral context beyond the annotations: the ID provenance caveat ('NOT a food_entry_id from the diary page'), the safety cap meaning of max_matches, case-insensitive matching, and that the return is a JSON describing removed entries.

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 organized into purpose, two modes, args, and return. Every sentence contributes useful information; there is no filler. The front-loaded purpose and mode breakdown make it easy to scan while preserving necessary detail.

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?

The description fully covers mode selection, parameter semantics, default behavior, matching semantics, and return value for this destructive operation. Given the output schema exists and annotations mark destructiveness, nothing an agent needs to call this tool correctly is missing.

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?

Even though the schema already has property descriptions, the tool description adds crucial meaning: it explains that entry_id is the UUID returned by mfp_add_food_to_diary, clarifies how name_contains works, states max_matches acts as a safety cap with default 1, and notes the date default. This meaningfully exceeds the schema's bare descriptions.

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 opens with a specific verb and resource: 'Remove (delete) one or more food entries from your diary.' It then clearly distinguishes two operation modes (precise by entry_id, fuzzy by name_contains), making it easy for an agent to tell this apart from related tools like mfp_delete_meal.

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 explicit guidance on when to use each mode: 'Use this when you already know the ID' for entry_id, and describes the fuzzy matching flow for name_contains. It does not explicitly contrast against sibling tools such as mfp_delete_meal, but the internal mode selection guidance is strong and unambiguous.

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