mnemosyne_agenda_update

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

With no annotations provided, the description carries the full burden and does so thoroughly. It discloses partial-update behavior (omitted fields untouched, null clears), strict refusal of unreadable start/end times, refusal of unsupported cadences, environment-dependent execution (headless daemon vs app running), and the required scope: agenda:write.

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 description front-loads the primary purpose and then packs prerequisites, error behavior, and environment notes into a compact paragraph. Every sentence adds operational value, with no filler or repetition.

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 complex tool with a nested changes array, no output schema, and no annotations, the description covers the essential decision points: how to identify the appointment, how omitted/null fields behave, what inputs are refused, and whether the daemon is required. The only minor gap is atomicity across the array, but that is not essential for correctly invoking the tool.

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?

The schema already documents every field (100% coverage), so the baseline is 3. The description adds a global update rule 'a field you leave out is left alone; passing null CLEARS it' and instructs the agent to source event_id from mnemosyne_agenda_list, which goes beyond the schema by clarifying omission vs null semantics.

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 opens with the verb 'CHANGE' and names the exact resource: an appointment already in the human's calendar. It enumerates the supported mutations (move, rename, add/drop reminders, start/stop repeating) and explicitly says appointments are identified by the id from mnemosyne_agenda_list, making it clearly distinct from add/remove/list siblings.

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?

The description gives an explicit prerequisite: call mnemosyne_agenda_list first to obtain the appointment id. It also provides operational context such as null-clears-field semantics and the daemon/running-app requirement on dev installs vs npm installs, but it never explicitly names when-not alternatives like agenda_add or agenda_remove.

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