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

Annotations declare only readOnlyHint=false and destructiveHint=false, and the description adds substantial behavior beyond that: one evaluation per stage with replacement semantics, server-side final/interim determination based on task closure, and the fact that the factor is a recommendation that does not alter tracked time. Visibility of the comment to all task viewers is also disclosed. This is exactly the kind of context annotations cannot carry.

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 front-loaded sentence that leads with purpose and then layers the write/visibility semantics. It is dense but every clause is informative; slight overpacking into one sentence keeps it from a 5.

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?

With no output schema, the description adequately covers the mutation's outcome (final/interim marking, replacement of prior evaluation) and the non-effect on tracked time. Required rulesRevision is left to the schema, which is acceptable given full coverage.

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 baseline is 3, but the description adds meaning beyond the schema: the factor is a recommendation that does not change tracked time, and the comment is visible to all who see the task. It does not explain rulesRevision, but that is documented in the schema.

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 ('Saves a task stage evaluation') plus the data it carries (bonus factor, comment). It is clearly distinguishable from siblings like task_evaluation_context or evaluation_rules, which are read/config tools rather than the act of recording an evaluation.

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 an explicit triggering condition: 'when the user asks to evaluate work.' That is clear context for invocation. It does not, however, name an alternative tool or state when-not-to-use (e.g., versus reading task_evaluation_context), so it stops short of full routing guidance.

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