mnemosyne_agenda_update

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

Annotations already indicate destructiveHint=true, but the description adds substantial behavioral context beyond that: it explains failure modes (refuses unreadable start/end times, refuses invalid cadence), the effect of null on recurrence (drops series end), and environment-specific behavior (works on dev install via daemon, needs app running on npm install). This goes well beyond the annotation flags and gives the agent a clear picture of side effects and constraints.

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 is a single, dense paragraph that front-loads the core purpose and then covers prerequisites, semantics, failure handling, and environmental notes. Every sentence carries operational weight; there is no filler. While it is longer than strictly minimal, the complexity of the tool justifies the length, and it is organized logically.

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 mutation tool with destructiveHint=true and no output schema, the description is remarkably complete: it covers the required id source, the patch semantics, failure conditions, recurrence behavior, and the dev/npm install difference. An agent can correctly invoke this tool for any intended change without additional clarification. The only minor omission is the exact response shape, but that is not needed given the absence of an output schema.

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%, with each parameter having a detailed description (e.g., start time timezone semantics, null behavior for clearable fields). The description adds global semantics over the schema: 'A field you leave out is left alone, and passing null clears it' – a rule not per-parameter. It also clarifies the batch nature (up to 50 per call). This enhances the schema's guidance without redundancy.

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 a clear verb ('Change') and resource ('an appointment already in the user's calendar'), then enumerates the specific actions (move, rename, add/drop reminder, start/stop repeating). It distinguishes itself from siblings like mnemosyne_agenda_add and mnemosyne_agenda_remove by focusing on modification, and it explicitly references the id source (mnemosyne_agenda_list), making its scope unambiguous.

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 explicitly states the prerequisite: 'It names appointments by the id from mnemosyne_agenda_list, so call that first.' It also explains the semantics of omitted fields (left alone) and null (clears), which tells the agent how to construct change requests. However, it does not explicitly contrast with add/remove or state when not to use this tool, though the sibling names make that inference easy.

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