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

Beyond the annotations' readOnly/idempotent profile, it discloses a real dependency (needs the dashboard to read agent leases) and the degraded response when agents report via claim comments only ('it says it is not available'). It also states 'never fails: if a part cannot be read it says why,' which tells the agent it can call this without error handling — genuinely useful behavior no annotation conveys.

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 opening question is well front-loaded, but the body is a single sprawling construction enumerating three lists with nested clauses, which slows parsing for an agent skimming many tools. The information mostly earns its place, but it would benefit from the three list types being separated rather than run together.

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-shape burden and does so well: it names the per-row fields, the status vocabulary (recent, stale, done), check/merge state, and the housekeeping counts. What remains thin is how this view relates to the sibling 'what needs attention' tools, so an agent choosing among them still has to guess.

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 100%, with repo's owner/name format and limit's default and bounds documented in the schema itself. The description adds only that results are scoped 'for a repository' and that lists are 'most recently active first' / 'quietest first,' which is ordering rather than parameter semantics. 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 names a concrete resource and output shape: three lists (left-behind items, housekeeping counts, active work sorted by quiet time), each with specific fields like title, link, holding session, and status labels. It is clearly not a generic listing tool. It does not, however, distinguish itself from plausible siblings such as almost_done, needs_you, or live_sessions, which also sound like 'what's outstanding' views.

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 explicit triggers: 'when your human asks what was left unfinished, or before you pick work, to finish or hand on what is already started,' plus a follow-up rule to check the item with board and claim it as usual. What is missing is any negative routing — no statement of when to prefer almost_done, needs_you, or who_holds instead.

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