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

Annotations already declare a non-idempotent, non-destructive write with openWorldHint=false, so the safety profile is covered. The description usefully reveals the two input modes (minutes ending now/at end, or start+end), but does not discuss permissions, overwrite behavior, or how duplicates are handled.

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?

Two tight sentences with the core mode distinction front-loaded and no filler. Dense but readable, though the trailing activity list is somewhat elided and cryptic.

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 12-parameter mutation tool with no output schema, the description covers the central time-entry semantics but omits the meaning of many supporting parameters. It is adequate for the common case but incomplete against the schema's complexity.

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 67%, and the description adds real meaning for the time parameters (minutes vs start+end HH:MM on a date). It says nothing about area, weight, exclusive, itemId, stepId, leverId, projectId, or the required 'task', leaving several parameters undocumented in both places.

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 past time') and constrains scope to untimed past time, which implicitly separates it from start_session/stop_session. It is clearly about logging a session, though it does not explicitly name the timed siblings it competes with.

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 condition 'past time that was not timed' gives implied guidance on when to use this versus live timers, and the activity list (calls, children, workout, paid work, away work) frames typical use. However, no alternative sibling is named and no when-not guidance is given.

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