Read Service Jobs

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered; the description adds materially beyond that by explaining that `searched` reports where Monitor looked and that 'nothing is invented when nothing is found', which tells the agent how to interpret empty results. It also discloses that failure texts are unavailable here and require another call, which prevents a wrong follow-up assumption.

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 core action and the supported backends, then moves to return contents and the `searched` caveat. The long enumeration of returned fields is dense but each item is load-bearing given there is no output schema; only minor tightening would help.

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, and the description carries that burden well by enumerating the returned data (finished/failed runs per step, failure share, p95, schedules, queue depth, consumers, dead letters) plus the honesty caveat on `searched`. Combined with the named alternative for failure texts and the supported service types, an agent has what it needs to call this correctly; only parameter meanings remain thin.

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 only 17%: just `range` is documented, while env, region, workspaceSlug, appSlug and serviceName carry no schema description. The description does not compensate — it never explains which service types map to serviceName, what `region` scopes, or how `env` interacts with the Redis/RabbitMQ lookup, so five of six parameters remain semantically undefined.

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 ('finds the job library the service uses and reads it') and enumerates exactly which backends are covered: BullMQ, Sidekiq, Celery state in Redis, RabbitMQ queues, and job lines in the service's own logs. It also names the sibling that covers the adjacent case (readServiceJobDetails for failure texts), which lets an agent distinguish it from readServiceLogs and readServiceJobDetails without opening a 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 clear applicability ('works on a worker, a Redis or a RabbitMQ service') and routes the agent elsewhere for one adjacent need ('failure texts need readServiceJobDetails'). It stops short of explicit exclusions such as when to prefer readServiceLogs or retryServiceJobs, so the when-not guidance is implied rather than stated.

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