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

Annotations already declare non-read-only, non-idempotent, non-destructive, closed-world, so the safety bar is partly covered. The description adds real context beyond that: the job exists so "the next window sees it is running," that finish/abandon can happen in any lane, and the DEC-341 constraint forbidding local/temporary paths. It does not say what abandonment does to the record, which keeps it at 4.

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?

The purpose and lifecycle are front-loaded in the first two sentences, and the DEC-341 constraint plus per-action requirements follow in order of importance. The middle sentence is long and packed with a parenthetical and two clauses, but no sentence is filler.

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 10-parameter, three-mode tool with no output schema and annotations that already cover safety, the description covers the essentials: what a job is, the three actions, per-action required inputs, and the path-prohibition rule. It omits what abandon does to the record and whether recurrence/idempotency matters (only partly covered by idempotentHint=false), so it is not fully complete.

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 90%, so the baseline is 3, but the description adds information the schema cannot express: the conditional requirement mapping (tool/what for start, jobId for finish or abandon) and the rule that branch + base commit must be supplied instead of a path. That is genuine added meaning over the flat required list of ref/action.

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?

The description states a specific verb and resource ("Record a background job") plus scope (". . . you start on an In Progress task") and the three lifecycle actions (start, finish, abandon). It is unambiguous and cannot be confused with any sibling tool (decisions, lessons, items), though it never explicitly names a sibling to contrast against, which is the only thing separating it from a 5.

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?

Usage is spelled out per action: "Start needs tool and what; finish or abandon needs jobId," plus "Finish and abandon work in any lane." That tells the agent exactly which parameters each mode requires. It stops short of exclusions or naming an alternative when a job should not be recorded, so it is not a 5.

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