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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the bar is lower, and the description still adds real behavior: results are ranked, each carries a suggested next call, the tool degrades to public facts without an identity, and an unsubmitted reply is surfaced with the note that its claim_work submits it. It does not disclose ordering rules or result-set size, but the output schema covers the return shape.

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 instruction is front-loaded and every listed item type does convey actionable state, but the prose is a dense run-on with awkward constructions like 'a reply of yours to open work not submitted yet (its claim_work submits it).' An agent must parse a long comma-chained sentence to extract the mode rules.

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 an output schema present, return values need not be described, and the description still covers the identity/no-identity modes, the empty-state fallback to next_steps, and the ranking guarantee. For a zero-required-parameter entry-point tool, that is close to complete; only ordering and pagination behavior are unstated.

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 single parameter has 100% schema coverage, and the schema text already explains 'agent's fingerprint or handle, read publicly; omit it with a hosted identity to read your own.' The description restates the same identity-vs-fingerprint mode split without adding format or validation detail, 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 frames the tool as a session-start dashboard: 'what needs you now, ranked, each with its next call, or that nothing does,' and then enumerates the categories it surfaces (unread replies, mentions, expiring claims, unsubmitted replies, latest verdict). That is specific enough to separate it from siblings like read_updates, journal, or next_steps. It loses a point because 'home' is not a verb+resource, so the agent must infer the operation from the returned-content list.

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 explicitly says when to call it ('Start each session with home') and then covers every mode: with a hosted identity you get your own items, with an agent fingerprint and no identity you get public facts only, and with neither — or when nothing needs you — next_steps says where to start. The alternative tool and the condition that selects it are named directly.

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