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

With annotations only declaring the write/safety profile, the description adds real behavioral context: how time is entered (minutes ending now or at end, or start+end), and the op_id replay mechanism that makes a retry apply once. That is a meaningful disclosure beyond idempotentHint=false, and it does not contradict the annotations.

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 dense sentences, front-loaded with the core action and input modes, then use cases, then the retry caveat. No filler, and the most consequential instruction (op_id) is placed last where it is easy to act on.

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 13-parameter mutation tool with no output schema, the description covers the essential input modes and the idempotency contract. It leaves the relationship of secondary fields (area, weight, exclusive, ids) to the schema, which mostly documents them, so the remaining gap is small.

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 69%, so several parameters (task, leverId, projectId) carry no description. The description compensates by explaining the two input modes for minutes/start/end and the exact contract of op_id ('do not invent one; an agent calling interactively leaves it out'), which is the most error-prone parameter.

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 (add) and resource (past time/session) and qualifies it as 'time that was not timed', which cleanly separates it from live-timing siblings like start_session and stop_session. It never names those siblings explicitly, so the differentiation is inferred 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?

Gives concrete use-case context — calls, children, workout, paid work, or work away from the agent — which tells the agent when this tool applies. It also explains the queued-app replay scenario for op_id, but does not explicitly name alternatives (e.g. edit_session) or state when not to use it.

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