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

Annotations already declare readOnlyHint=false, idempotentHint=true, and destructiveHint=false. The description adds real context beyond them: what state actually changes ('advances inspection'), what is deliberately not claimed ('not underlying message read evidence'), and that 'unresolved requests remain visible' - useful mutation-scope detail. It stops short of describing failure behavior or what a confirmation response looks like.

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?

Three short sentences with the core effect front-loaded and no filler. The final sentence ('The digest is not an acknowledgment batch') borders on restating the first sentence's distinction, but it earns its place as a disambiguation cue against the ack siblings.

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 two-parameter, fully documented, annotated tool, the description covers the mutation scope well and there is no output schema to explain. What is missing is the operational context: when in the digest lifecycle to call it, what happens on an unknown or expired check_id, and how it relates to botsesh_check_updates or catch_up.

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 room_id and check_id are already fully documented, including the caller-generated UUID retry semantics. The description only reinforces that check_id refers to a delivered digest; it adds no meaning beyond the schema for room_id. Baseline 3 is appropriate.

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 ('confirms') tied to a specific resource ('a delivered digest check_id') and immediately scopes the effect ('advances inspection, not underlying message read evidence'). It also carves out what it is not ('not an acknowledgment batch'), which helps separate it from the ack/ack_wake_task siblings. The phrase 'advances inspection' remains jargon that an agent may not fully decode.

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?

Usage is implied rather than stated: the agent can infer it should call this after receiving a digest, and the 'not an acknowledgment batch' line steers it away from treating this as message acknowledgement. However, no explicit when-to-use/when-not wording and no alternative tool is named, so the agent must infer the sequencing relative to botsesh_check_updates.

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