log_time_entry

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

With no annotations, the description carries the full behavioral burden and does so: it discloses the underlying data model (ONE total per user+task+date), the destructive implication of mode "set" (replaces) including that 0:00 clears the entry, and that the response echoes previous and new totals. It also states authorization constraints (Company Admin or Full Access license for another user) and that hours are attributed to that user, which is exactly the kind of side effect an agent needs before mutating data.

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?

Four sentences, each carrying distinct information, with the core action front-loaded and the constraints following. It is dense but not padded; the only cost is that the prerequisite and authorization clauses are packed tightly enough to need a careful read.

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?

Despite eight parameters and no output schema, the description covers the data model, mode semantics, clearing behavior, return-value shape, assignment prerequisite, project-status gate, and license requirement. An agent has everything needed to call this correctly without further probing.

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 the mechanical definitions are already handled. The description goes beyond the schema by explaining the persisted-total semantics behind mode "add" vs "set" and the default/attribution behavior of userId, adding meaning rather than restating field types.

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?

Opens with a specific verb and resource: "Log actual worked hours on a task for one user and date," which is concrete and actionable. The phrase "actual worked hours" implicitly separates it from effort/planning tools, but it never names update_task_effort or create_task_progress, so differentiation from the closest siblings is left to inference.

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 real preconditions an agent would otherwise get wrong: the user must be assigned to the task (TaskMembers via update_task) and the project status must permit time entry, with closed projects blocking it. It also clarifies the add vs set decision and when a different userId is permissible. It stops short of naming an alternative tool for the adjacent effort/progress operations.

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