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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the write nature is covered. The description adds no behavior beyond them: it does not say that each call appends a new observation (idempotentHint=false, so duplicate submissions are not deduplicated), that observations feed derived inventory quantities, or whether an entry can later be edited or reversed. The listed event words largely mirror the observationType enum already in the schema.

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 front-loaded sentence with zero padding — the intent lands immediately. It is arguably too terse for a six-parameter, state-mutating tool, but nothing in it is wasted or buried.

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?

No output schema exists, so the description need not describe return values, and the schema covers all six parameters. What is missing is domain context for a tool that shifts household inventory: how observationType values affect stock levels, and how colloquial cases like "used" or "gone" map to EstimatedConsumed versus ConfirmedGone. Adequate to invoke, incomplete to invoke confidently.

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 100%, so every parameter is already documented, including the note to omit foodKey because it is derived from displayName. The description contributes no additional meaning about quantity/unit interaction, which storageLocation to choose for ambiguous cases, or how quantity is interpreted per observationType. Baseline 3 is the right call when the schema carries the semantics.

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 ("Record") and a specific resource ("what happened to a food at home"), then enumerates observation kinds: bought, seen, used, frozen, thrown out, gone. That is enough to separate it from read-oriented siblings like get_inventory. It falls short of 5 because the colloquial verbs are never mapped onto the actual enum values, and two enum members (ManuallyAdjusted, LeftoverCreated) are never hinted at.

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?

Usage is implied by the framing "what happened to a food at home" — you call this when an event occurs rather than when you want to read state — but no alternative is named. Siblings such as get_inventory or merge_pantry_foods are never referenced, and there is no statement about when not to log an observation (e.g. correcting a prior entry).

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