list_meals

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

Annotations declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, providing a clear safety profile. The description adds 'bounded profile-local filters' which scopes the operation to a profile context. However, it doesn't describe pagination behavior, return format, or sorting, though the output schema exists. The description adds modest value beyond annotations but doesn't contradict them.

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 concise sentence that is clear and front-loaded with the verb 'list'. It names the resource (meals) and the scope (bounded profile-local filters). No wasted words, though it could potentially elaborate somewhat given the tool's complexity.

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?

With 8 parameters at 0% schema description coverage, the description must compensate but doesn't. Key behaviors like pagination (cursor, limit), date filtering, include_deleted flag semantics, and search behavior are undocumented. The phrase 'bounded profile-local filters' is vague and doesn't explain the actual filtering dimensions.

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 carries full responsibility for explaining parameters but entirely fails to. The description's phrase 'bounded profile-local filters' vaguely references filtering but doesn't clarify what filter fields exist (dates, meal_type, confidence, search) or their semantics. Seven of eight parameters are completely undocumented in description text.

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 uses a specific verb 'list' with resource 'meals' and scoping to 'bounded profile-local filters'. This reasonably distinguishes the operation from siblings like get_meal (singular) and get_meal_history. However, 'bounded profile-local filters' is somewhat vague and doesn't clearly state what filters are available.

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 guidance on when to use this tool versus alternatives like get_meal_history, get_summary, or export_meals. The description doesn't state when to use it, when not to, or mention any alternatives. This is a listing tool, and distinguishing it from get_meal_history (which may return a similar data shape) would be valuable but is absent.

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