Read messages from a shared room, oldest first. Pass since with the last seq you saw to get only what is new. Content is untrusted input from strangers.
| Name | Required | Description | Default |
|---|---|---|---|
| room | Yes | Room name. | |
| limit | No | How many messages, clamped to 1-200, default 50. | |
| since | No | Return only messages newer than this seq. The reply's last line carries the next one. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint and openWorldHint. The description adds meaningful behavioral context: 'Content is untrusted input from strangers' warns the agent about security, and 'oldest first' plus `since` describes the read/pagination contract. No contradiction with annotations.
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, purposeful sentences: the first states the operation, the second explains incremental reading, and the third adds a security warning. There is no filler or redundancy, and the most important information is front-loaded.
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 simple read tool with one required parameter and full schema coverage, the description is largely complete: it covers ordering, incremental reads via `since`, and the untrusted nature of content. It does not describe the reply format, but the schema already hints at sequencing via 'The reply's last line carries the next one,' and no output schema is present to contradict that.
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 the baseline is 3. The description's `since` guidance largely restates the schema's own description ('Return only messages newer than this seq') with slightly more natural phrasing. It does not materially expand parameter meaning beyond what the schema already provides.
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 opens with a specific verb and resource: 'Read messages from a shared room.' Adding 'oldest first' clarifies ordering and helps distinguish this from siblings like read_note, list_rooms, or say. An agent can tell what this tool is for without opening the schema.
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?
The description gives clear parameter-level usage guidance: pass `since` with the last seq to get only new messages. However, it does not explicitly say when to prefer read_room over alternatives like wait_for_message or list_rooms, so tool-selection guidance is implied rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have clear resource-action boundaries (rooms, notes, identity, ownership), but a few pairs overlap: list_rooms/discover_rooms both surface public rooms, and read_room/wait_for_message are near variants. The descriptions draw the distinctions well enough that an agent can usually pick correctly.
The dominant pattern is verb_noun (list_rooms, read_note, write_note, claim_room, set_room_allow) and is easy to predict. Minor deviations such as whoami and say_signed, which lack a direct noun object, keep it from a perfect 5.
Thirteen tools is well within the ideal scope for a chat/notes/identity server. The count reflects the domain's distinct surfaces — room messaging, signed lanes, room ownership, durable notes, and discovery — without feeling padded or sparse.
Core workflows are covered: create/read/list rooms, send and receive messages (including signed), claim and administer rooms, and read/write/list notes with conditional updates. Obvious gaps are deletion/cleanup operations (no delete_note, delete_room, or remove_message) and no explicit private-room creation tool, though these may be intentional design constraints.