Record a bag swap

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

Goes well beyond the annotations by disclosing a non-obvious side effect: a date earlier than the current swap removes the later swap record. It also reveals the return value (the bag report) and the requirement that relative dates be resolved by the caller. The only gap is that this removal behavior sits in slight, unreconciled tension with destructiveHint=false, which an agent could misread as 'nothing is ever deleted'.

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?

Three sentences, front-loaded with the core action and return value, then the default behavior, then the correction edge case. Every sentence carries distinct, load-bearing information; nothing is restated from the schema.

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?

There is no output schema, and the description compensates by stating that the bag report is returned. Combined with the date-format guidance and correction semantics, an agent has everything needed to invoke this two-parameter tool correctly.

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 formats (YYYY-MM-DD / YYYY-MM-DDTHH:MM / ISO 8601) and the note example are already there, giving a baseline of 3. The description adds genuine meaning beyond that: the default-when-omitted behavior and the instruction to pre-convert relative dates, which the schema does not say.

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 ('Record that the user changed the robot's dust bag') and immediately names the return value, making it clearly distinguishable from the read-only sibling matic_bag_report. An agent knows this is the write counterpart to the bag report without opening the 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?

Explicit when-to-use rules: omit `when` for today/now, pass a concrete local date for an earlier day, and convert relative expressions like 'yesterday' yourself. It also adds an alternative use case ('use this to fix a wrong date too'), so both the normal and corrective paths are covered.

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