export_meals

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

Annotations already declare destructiveHint=true and readOnlyHint=false, signaling this tool can write/destroy. The description adds that it can write 'to a local path' and mentions overwrite behavior is available, which aligns with the destructive hint. However, it doesn't disclose what gets overwritten, file permission requirements, or side effects beyond the annotation. The description adds modest context over the destructiveHint.

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?

A single efficient sentence that front-loads the purpose and key options (JSON/CSV, inline/path). No wasted words. However, it's arguably under-specified for the tool's complexity, so while concise, it could trade some brevity for more guidance on filters and output behavior.

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 tool has a destructiveHint, an output path (potentially writing files), and a nested filter object, yet the description offers minimal detail on these. An output schema exists, so return values are covered, but the write-to-disk behavior and overwrite semantics (which have destructive implications) are not explained. For a tool of moderate complexity with write behavior, this is adequate but leaves gaps around what output_path writes and overwrite consequences.

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 0%, so the description must compensate but doesn't detail any parameter semantics. However, the schema itself is rich with titles, defaults, and enums for the nested MealFilterRequest. Since the nested filters object is complex (8 fields with defaults and enums), the description could add value by explaining how filters bound the export, but relies on the schema. Baseline for 0% coverage would be low, but the schema's self-documenting titles lift comprehension. The description 'bounded meal page' does hint that filters limit the export scope.

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 states a specific verb (Export) + resource (meal page) and clarifies output formats (JSON or CSV) and delivery modes (inline or to a local path). It's clear what the tool does, though it doesn't explicitly distinguish it from siblings like list_meals or get_meal. The phrase 'bounded meal page' hints at pagination/filtering scope but could be more explicit.

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 implies this is for exporting filtered meal data, but gives no explicit when-to-use vs alternatives. With siblings like list_meals and get_meal, there's no guidance on when export is preferred over listing. No exclusions or alternatives are named, leaving the agent to infer usage context.

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