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

Annotations only declare the safety profile (readOnly=false, destructive=false, openWorld=false); the description adds real behavior: one evaluation per stage, replacement of prior evaluation, server-side final-vs-interim labeling driven by task closure, and that the factor is advisory and does not alter tracked time. It also discloses visibility ('visible to all who see the task'), which no annotation conveys.

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?

Front-loaded with the action and trigger, and every clause carries information (replacement rule, final/interim, advisory factor). It is dense to the point of one long semicolon-chained sentence, which costs a little readability.

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?

No output schema exists, but the description covers the essentials an agent needs: what gets persisted, the one-per-stage replacement rule, how the server classifies the evaluation, and that the factor is non-binding. It is only slightly short on things like permission requirements or the source of rulesRevision beyond the schema note.

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 description coverage is 100%, so the baseline is 3, but the description adds meaning the schema lacks for two key params: 'factor' is a recommendation that does not change tracked time, and 'comment' is visible to everyone who sees the task. The replacement/one-per-stage rule also constrains how a call is composed.

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 precise verb+resource ('Saves a task stage evaluation') along with the payload it carries (bonus factor, comment) and the trigger. An agent can tell this is the write counterpart to the read-side sibling task_evaluation_context without opening either 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?

Gives an explicit activation condition ('when the user asks to evaluate work'), which is more than most tools offer. It does not, however, name the read-side alternative (task_evaluation_context) or state any exclusions/preconditions, so a 5 is not earned.

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