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

Annotations only declare non-idempotent, non-destructive writes; the description goes further by disclosing the side effect that an existing timer is stopped and logged with a name, which is the key behavioral risk an agent needs to know before calling. It also discloses the return value (start time) and that the rate applies to this timer only, though it says nothing about permissions or failure modes.

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 short sentences, zero filler, with the core action and its single-timer constraint front-loaded. The rate note is the only parameter detail included and it is the one most prone to unit errors.

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?

There is no output schema, so the description carries the return value and does so ('return the start time'). The single-timer side effect — the most consequential behavior of this tool — is covered, leaving only minor gaps such as what happens with tags/task persistence across a replaced timer.

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%, so all five parameters are already documented, including the rate's number-or-spoken-words form and project fallback behavior. The description's addition that rate is in MAJOR units reinforces an implicit schema example rather than introducing new semantics, so the baseline applies.

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?

Uses a specific verb and resource ('Start a stopwatch for work on a project') and states the immediate effect (returns the start time). The 'only one runs at a time' clause distinguishes it from the read-only timer_status sibling, so an agent can pick it without opening another schema.

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 explains what happens when a timer is already running (it stops and logs the previous one, naming it), which implicitly tells the agent when this is safe to call. However, it never names timer_stop as the way to end work or contrasts this tool with entry_log for recording time after the fact — both plausible alternatives an agent has to choose between.

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