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

Going well beyond the readOnlyHint/idempotentHint annotations, it discloses result ordering (most urgent first, dashboard order), the shape of each item (kind, severity, subject with number/title/link, one-line reason), degraded-run signals ('still reading pull request states', 'could not make a check'), and an explicit no-failure guarantee with the reason surfaced instead. These are exactly the behavioural facts an agent could not get from annotations or schema.

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?

Purpose is front-loaded and nothing is pure filler, but the ten-category enumeration is packed into one very long sentence that is hard to scan and partially duplicates itself with the item-shape sentence. The scope detail earns its place; the packaging does not.

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 carries the return-value burden itself and does so: item fields, ordering, degraded states, and the never-fails behaviour are all covered. An agent has everything needed to call it and interpret the result.

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 repo (owner/name, optional when the token covers one repository) and limit (default 20, max 100) are already fully documented. The description adds nothing about either parameter, so the baseline 3 applies.

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 gives a specific verb and resource ('Lists what needs a person on a repository') and then enumerates the ten item categories it returns, which sharply delimits its scope against neighbours like almost_done, left_behind and quick_wins. It never names a sibling tool explicitly, so the boundary is inferred from the enumeration rather than stated, which keeps it just short of a 5.

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 states two concrete use cases: when the human asks what needs attention, and before picking work so you fix blockers first. That is clear situational guidance with an ordering rationale, but it offers no exclusions or named alternatives for the overlapping sibling tools.

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