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

Adds substantial behavior beyond the annotations: ingredient-level decomposition, one entry per ingredient in a single meal, all-or-nothing writing ('Nothing is written unless every part resolves'), a 20–60 second latency budget, and a described reply with entryIds, per-part entries, assumptions and totals. What it does not cover is why destructiveHint=true matters here — nothing is said about undoing or overwriting a logged meal, nor whether a retry duplicates entries despite 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?

Front-loaded with the action and an example, then behavior, then time handling, then the return shape — a sensible order with no filler sentences. It is dense and long for a description, and the time paragraph packs four cases into one sentence, but every clause carries information an agent needs.

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?

For a six-parameter write tool with no output schema, the description covers input expectations, atomicity, latency, time resolution, and return contents including the assumptions and totals — enough to call it correctly and set expectations. Remaining gaps are recoverability (can a wrong log entry be reverted via joiva_delete_log_entry?) and duplicate behavior on retry.

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 coverage is 100%, so the baseline is 3, but the description adds real meaning on top: the three time paths (loggedAt, date+meal placed at the meal's usual hour, date+time, and now by default) plus the rule that a past day without a slot or clock time is rejected rather than invented. That decision logic is not in the schema and directly shapes how an agent fills the optional date/meal/time parameters.

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?

States a specific verb and resource ('Log a meal the signed-in user described in their own words') and immediately illustrates with a concrete meal string, which makes the free-text nature unmistakable. It never names the adjacent structured logger (joiva_log_food) or joiva_log_meal, so the distinction from siblings is implied by 'in their own words' rather than stated.

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?

Clear about the input shape it expects (raw user wording, including amounts, exclusions, preparation) and firm about a constraint an agent would otherwise trip over: a past day without meal and time is refused. It does not explicitly say when to prefer joiva_log_food or joiva_log_meal instead, so routing between the three logging tools is left to inference.

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