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

Annotations already declare this as a non-read-only, non-destructive, non-idempotent, closed-world write, so the safety baseline is covered. The description adds real behavioral value beyond that: it flags when a feed overlaps recorded sleep, states that the response carries a `confirmation_summary` sentence, and explains that passing `idempotency_key` turns a retry into a no-op — a useful nuance relative to idempotentHint=false.

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 mode breakdown is front-loaded in the first sentence, with response and idempotency behavior trailing in short clauses. Every sentence carries information an agent needs; there is no filler.

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 no output schema, the description still tells the agent what comes back (a sleep-conflict flag and a `confirmation_summary`), and annotations cover the mutation/safety profile. Nothing material for correct invocation is missing, aside from the minor omission of `note`.

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% and there are 8 parameters, so the description carries the full burden — and it does. It supplies the value set for `kind`, the mutually alternative `ml`/`oz` for milk, `foods` plus the `meal`/`snack` choice for `meal_type`, the ISO format for `at`, and the retry semantics of `idempotency_key`. Only `note` is left undocumented.

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 names a specific verb+resource ('Log a feed') and then decomposes it into its three distinct modes (milk, breast, solid) with the data each mode requires. This is enough for an agent to distinguish it from siblings like log_sleep, log_nappy, or log_measurement without opening any schema.

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 clear conditional guidance for choosing the right `kind` and the fields that go with it (ml/oz for milk, foods + meal_type for solid), which is genuinely useful. However, it never states when to prefer this tool over a sibling or when not to call it, so usage is implied rather than explicit.

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