job_history

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

With no annotations supplied, the description carries the full burden and does disclose non-obvious behavior: ids are walked downward from the newest known id in batches, start times are server-local from the protocol, and scheduled jobs are excluded unless explicitly requested. These are meaningful implementation facts an agent could not infer from the schema. It omits any mention of cost/latency implications of the id-walking strategy, permissions, or failure behavior, which keeps it from a 5.

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 is front-loaded in the first clause, and every subsequent segment carries real information (returned fields, exclusion rule, filter list). The heavy parenthetical nesting, especially the id-walking aside, makes it dense to parse, 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?

There is no output schema, so the description correctly compensates by enumerating the per-job return fields, and it covers the default limit, the exclusion rule, and all four filter parameters. What remains thin is the meaning of individual returned values (units of 'size', what 'completion' represents), but for a read-only history query this is close to 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 description coverage is 100%, so the baseline is 3. The description mostly mirrors the schema ('plan (name or id)', 'limit (default 50)') but does add value on status by clarifying it matches 'status or completion' with concrete examples (completed, running, failure), which the schema does not. Conversely, it is less precise than the schema on 'since', dropping the HH:MM form, so the net gain over structured data is modest.

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 opens with a specific resource ('Past jobs') and immediately distinguishes it from the sibling listing behavior ('P5's job listing only returns scheduled ones'), so an agent knows this is the historical view rather than the live job list. It then enumerates exactly what is returned per job (id, plan, task, status, completion, start time, size, files, source line), leaving no ambiguity about the tool's output shape.

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 description gives clear selection context: it explains that the ordinary job listing only returns scheduled jobs and that this tool walks ids downward to reach past ones, which effectively routes the agent here for history. It also states the exclusion rule ('Scheduled jobs are excluded unless status is scheduled') and lists all filters. It stops short of naming a sibling alternative explicitly or stating when-not to use it, so it is strong but not a full 5.

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