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

Annotations already declare idempotentHint=true, destructiveHint=false and readOnlyHint=false, so safety is largely covered. The description adds meaningful state context beyond that: the call releases a triage lease, which is the substantive effect an agent needs to know. It doesn't say what happens when no session is active (error vs. no-op).

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?

Two sentences, action first, then invocation conditions; no filler and nothing buried at the end.

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?

For a zero-parameter lifecycle terminator whose annotations cover safety and idempotency, this is close to complete. Minor gaps remain: no mention of anything returned on success, and no clarification of its relationship to the end_triage sibling.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; the empty schema is fully self-explanatory. Baseline 4 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?

States a specific verb and resource ('Ends the inbox zero session') and adds that it releases the triage lease. It clearly reads as the terminator of the inbox_zero family (start/decide/wait), though it never distinguishes itself from the sibling end_triage, which could plausibly end the same kind of lease.

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?

Gives two concrete trigger conditions: 'when inbox_zero_decide returns an empty batch, or when the person is done.' That is explicit positive guidance. It does not say which tool to use instead when a session should be torn down for other reasons (e.g. end_triage) or what to do if no session is active.

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