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

The description discloses the crucial side effect that jobs are marked as seen, and gives the opt-out (mark_seen=false) — which explains and justifies the readOnlyHint=false annotation. It also discloses ordering and the last-check default. It stops short of describing return shape or limits, but against annotations it adds real behavioral value.

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?

Two compact sentences, front-loaded with the core behavior, then the mutation caveat. Every clause carries information: scope, ordering, grouping, side effect, and opt-out.

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 'best first, per alert' gives a rough shape and the seen-marking side effect is covered. Minor gaps remain: no statement of what a result entry contains or what happens at the 25-job limit, but an agent has enough to call it correctly.

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 75%, and the description supplies meaning for the undocumented mark_seen flag ('marks them as seen unless mark_seen=false') as well as restating the since default. It also implies per-alert grouping that shapes how alert_id and limit behave, adding context beyond the schema text.

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 resource (new jobs for the user's alerts) and a specific temporal scope (since last check, or a given time), plus ordering ('Best first, per alert'). It is distinguishable from siblings like past_alerts or my_jobs by the 'what's new since last check' framing, though it never explicitly says 'jobs' beyond the tool name.

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 when-to-use is implied by 'since their last check' (a polling/what's-new use case), but no alternative is named and there is no explicit when-not guidance — e.g. nothing says to use past_alerts for already-seen items or search_jobs for arbitrary queries.

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