check_habit

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

With no annotations at all, the description carries the full behavioral burden, and it does disclose the single most surprising trait: the default is not always +1, because at an already-met goal it decrements by 1 (a toggle). That is valuable and non-obvious. It says nothing about whether the counter can go below zero, what permissions or rate limits apply, or what the call returns, so it only partially covers the burden.

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?

A single compact sentence front-loads the action, then the default behavior, then the override. The nested parenthetical about mobile tap behavior is dense but earns its place by justifying the toggle rule. No filler.

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 two-parameter counter tool with no annotations and no output schema, the description covers the core semantics but leaves gaps an agent would want: what id is, whether values can go negative, and what the response looks like. Adequate for the tool's simplicity, but not complete.

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 description coverage is 0%, so the schema only supplies types and a null default. The description compensates for delta by saying it can explicitly specify an increase or decrease, which explains the null-vs-explicit distinction the schema cannot. It never says what id refers to (presumably the habit id) and gives no sign convention or range for delta, so the compensation is partial.

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 gives a concrete verb and resource: '打卡一次' (check in once) on a habit, which clearly separates it from add_habit, update_habit and delete_habit in the sibling list. It does not name those siblings explicitly, so the differentiation is inferable rather than stated.

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 only implied: the note that the default matches 'tapping once on the phone' tells the agent this is the progress-recording action rather than a habit-definition edit. There is no explicit when-to-use or when-not guidance, and no routing to update_habit or list_habits when a different outcome is wanted.

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