write_dumbbell_load

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

Annotations declare destructiveHint=true, and the description adds real behavioral consequences beyond them: already-logged workouts retain their logged meaning, while records and history compare sessions under the current meaning (a retroactive reinterpretation). It does not cover permissions or how to revert, but the disclosure of retroactive comparison effects is exactly the extra context annotations cannot supply.

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 core concept is front-loaded in the first clause, and the semicolon-separated sentences each carry distinct information (meaning options, volume/history effect, logged-workout behavior, routine override). It is somewhat prose-heavy and colloquial ('as, how it always worked'), but there is little genuine waste.

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 destructive, open-world write with two params and no output schema, the description covers semantics, retroactive effects, and the routine-level alternative reasonably well. It leaves open the tension between the required exerciseId and the described global default, and says nothing about authorization or scope, so an agent still has unresolved questions before calling it.

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 50% — exerciseId is documented in the schema but 'mode' has only an enum with no descriptions. The description compensates by decoding all three enum values ('each' = per dumbbell, 'total' = both together, 'as' = as entered) and noting the volume/history implications, which the schema does not. It adds no guidance for exerciseId and does not resolve whether the setting is global or per-exercise, so it falls short of full coverage.

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 explains the concept being configured (what a dumbbell/kettlebell weight means by default) and implicitly distinguishes itself from the per-routine setting in write_routine, but it never states the action in an imperative ('sets your default load interpretation'). The verb must be inferred from the tool name, leaving the purpose clear in topic but not in operation.

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?

It implies this is the account-wide default and points to the routine-level alternative ('a routine can choose its own (write_routine, dumbbellLoad)'), which is genuine routing guidance. However, it gives no explicit when-to-use condition, no preconditions, and no statement of who this setting applies to versus other settings tools like write_settings.

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