add_task

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

With no annotations, the description carries the full burden and does substantial work: it discloses that the task is persisted and returned with its id, that alarms fire at a default 3-minute lead (configurable), that alarms require a due time, and that the desktop app surfaces them. It omits error behavior for malformed syntax, tag auto-creation, and duplicate handling, keeping it below 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?

Front-loaded with the one-sentence purpose, then a compact token-by-token syntax list where nearly every clause carries a distinct rule. It is dense but not padded; the only slack is that token rules are comma-joined rather than separated, which slightly slows scanning.

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 single-parameter tool with no output schema, the description covers input syntax exhaustively and states the return value ('the stored task, with its id'). Remaining gaps are failure modes and side effects on tags, which are minor for a create operation of this shape.

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?

Although schema coverage is already 100%, the description goes far beyond the schema's one-line example by fully specifying the inline mini-language: #tag, !/!! priority, the full set of due-day forms, @15:30 time semantics, @none, and @alarmN's 0–1440 range. An agent can construct a valid argument purely from this prose.

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 ('Add a task') and immediately defines the input medium ('from one line of text'). The create-vs-complete-vs-update distinction is obvious from the verb, but the description never names or contrasts any sibling tool, so it lands at 4 rather than 5.

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?

Usage is implied by the verb — you call this when a new task must be created — but there is no explicit 'use this instead of update_task when...' guidance, no statement about prerequisites, and no mention of how to handle text that references an existing task. Adequate but inferential.

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