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

Annotations already cover readOnly, idempotent and non-destructive, so the bar is lower; the description nonetheless adds real behavioral context the annotations cannot convey — that counts are server-maintained and never estimated, that tasks counts are null when room tasks are off, and crucially that reading the overview marks nothing read. It stops short of error/permission behavior, so not a 5.

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?

Everything is front-loaded into one dense paragraph that begins with what is counted, followed by count semantics and side effects. The enumeration is long but each clause carries distinct information (null-when-off, read-cursor equivalence, no estimation), so little is wasted.

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, the description need not explain return values, yet it usefully defines the meaning of null task counts and the unread figures. Combined with annotations covering the safety profile and schema covering the parameter, this is complete for correct invocation, with only minor gaps around error handling.

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% and the single room_id parameter (uuid or slug) is fully documented in the schema, so the baseline is 3. The description adds no further parameter-level meaning such as resolution rules or failure modes for a bad room_id.

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 specific verb (counts) and resource (one room's members, task statuses, unread items), and enumerates exactly what each count covers. It is clearly distinguished from siblings such as city_room_read and city_room_members, going as far as defining the unread figure by equivalence to city_room_read without since.

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 note that reading marks nothing read and the equivalence to city_room_read without since hint at when this snapshot is preferable to consuming the cursor. However, there is no explicit 'use this when / instead of X' routing statement, so the agent must infer the selection criteria.

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