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

Beyond the readOnlyHint and destructiveHint annotations, the description reveals the live-server versus dashboard-fallback behavior, the project/runtime grouping semantics, and the rule that without account_token the most recent reporter is chosen. These are meaningful behavioral traits that an agent could not infer from the schema or annotations alone.

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 description is four dense sentences with no filler and is front-loaded with the core ranking behavior. It earns its length given the auth/fallback and runtime-grouping complexity, though it is fairly technical.

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?

It covers the main behavior, fallback, selection, and grouping, which is helpful since there is no output schema. But it leaves the account_token mechanism unexplained — it is not in the input schema — and doesn't detail the returned `your_projects`/`project_group` structure or how `limit` affects the result, so an agent could still call it with incomplete expectations.

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?

The schema already describes project, install_id, and read_token; the description adds selection semantics for `project` — dashboard name, 'name (runtime)', or install id — and explains runtime grouping under `project_group`. However, it references `account_token` which is not a declared parameter, and it says nothing about `limit` beyond the schema's default/min/max.

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 first sentence defines the tool as a 'triage ordering' that puts 'worst-rated and slowest screens first' with a one-line reason, which is specific and distinct in function from sibling tools like crash_risk or trend. It lacks an explicit verb like 'returns' and doesn't name a sibling, but the resource and ranking logic are clear.

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 useful behavioral context — live answers when read credentials are configured, a dashboard note otherwise, and project selection with account_token — but it never states when to choose this tool over a sibling or when not to use it. Usage is implied by the title and the triage framing, not stated explicitly.

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