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

With no annotations, the description carries the burden well: it discloses an OAuth requirement and scope (history:write), that this is a write to past-dated data, and that only location is changed while the 'went outside' flag is untouched. It omits whether a correction can be re-applied or undone and what happens for days outside the history range, so not a full 5.

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?

Four sentences, front-loaded with the effect and followed by the trigger, the input options, and the auth constraint — no filler. It is slightly dense with inline tool/field references, but each sentence contributes.

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 5-parameter past-dated mutation with no annotations and no output schema, the description covers auth scope, side-effect boundaries, and how to source the cityId. It leaves return/confirmation behavior and edge cases for out-of-range dates unstated, a minor gap since no output schema exists.

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; the description adds real meaning by expressing the either/or choice between a cityId from search_city and a lat/lon pair, a mutual-exclusivity relationship the flat schema does not encode. It does not spell out error behavior when both or neither are supplied.

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 ('Records where the signed-in user was over a range of past days') and names the observable it resolves ('their history stops assuming'). It is clearly distinguishable from get_my_history, which it references as the tool that exposes the assumed days.

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?

Gives an explicit trigger — the user corrects a stretch — and ties it to a concrete signal (`locationAssumed` from get_my_history) plus a UI affordance (history calendar correction stretches). It also names the prerequisite lookup tool search_city for obtaining a cityId.

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