create_reminder

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

With no annotations, the description carries the full burden and discloses meaningful traits: replacement rather than accumulation (one per person/node), non-mutation of the deadline, privacy scoping ('Private to the key owner'), and that times are instance-local. It stops short of saying what a successful call returns, what happens if the node has no deadline despite the stated precondition, or whether the reminder triggers a notification channel — gaps that matter for a write tool with zero annotation coverage.

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 tight sentences, front-loaded with purpose and followed by constraints; nothing is filler. Slightly dense with parentheticals, but each one carries a real constraint rather than restating the name.

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 4-parameter write tool with no output schema and no annotations, it covers purpose, prerequisites, replacement semantics, and the time-unit semantics well. Missing only return/confirmation behavior and the offset_days default — minor relative to what is supplied.

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 only 25%, so the description must compensate, and it does for the two parameters that need it: offset_days is defined by worked examples ('0 = on the deadline day, 1 = the day before') and time by format plus 'instance local time'. map_id and node_id remain bare, and it does not state a default for offset_days or acknowledge the schema's 0–30 bound.

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 ('Set a timed REMINDER for a map node') and pins down the coordinate system ('relative to its deadline'), which separates it cleanly from update_node and the create_event/create_calendar siblings. An agent knows exactly what object is being created and on what basis it is scheduled.

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 explicit preconditions ('the node must already have one (set it with update_node first)') and names the alternative for the case where the deadline is missing. It also sets a re-entry expectation ('One reminder per person and node (calling again replaces it)'), so the agent knows this is a replace-not-duplicate operation.

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