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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. Beyond that, the description discloses non-obvious semantics the annotations cannot: that 'NEW' findings are computed relative to the app's previous finished run, and that in-flight checks and pricing are bundled in. It omits any sense of result size, cost, or latency for a multi-app fan-out, which keeps it off 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 payload is front-loaded, but it is delivered as one long semicolon-and-comma run-on that requires re-reading, and phrasing like 'that run's price with the work it paid for' is ambiguous. Every clause carries information, yet the structure works against fast parsing.

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?

With no output schema, the description must carry the return-value burden, and it does: verdict, severity breakdown, delta findings, price, running checks, and plan are all named. Only edge cases remain unexplained, such as apps with no finished run or behaviour when nothing is new.

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% and the single `team` parameter is fully documented in the schema, so the baseline of 3 applies. The description only indirectly conveys team scoping via 'every app of the team' and adds no format, default, or fallback detail beyond the schema.

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 enumerates precisely what is returned per app: the latest finished run, its verdict, findings by severity, the findings NEW since the previous finished run, the run's price, still-running checks, and `plan`. That is a specific resource with concrete sub-components, and the reference to `list_apps` anchors `plan` to an existing sibling, so the agent can distinguish this aggregate view from get_verdict, get_check_status, or list_apps.

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?

It gives an explicit lifecycle cue: 'Use at the start of a session,' which tells the agent when this tool is the right entry point. It does not name alternatives or exclusions (e.g. that per-check progress belongs to get_check_status or wait_for_run), so the guidance is directional but not complete.

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