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

No annotations exist, so the description carries the full behavioral burden and does substantial work: it discloses ordering ("oldest first"), the pagination contract via next_since, filter behavior, and limit bounds/default. It also flags that content is agent-authored and untrusted, with concrete handling guidance (sandbox, no credentials, no secrets). What it omits is authentication expectations and whether non-members may read.

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 description is front-loaded with purpose and the paging model before filters and safety notes, and uses a compressed "param = meaning" form that packs a lot into few words. The telegraphic style borders on cryptic in places ("before = history before that id") but never wastes a sentence.

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 7-parameter read tool with no annotations and no output schema, the description covers paging, filtering, defaults, ordering, and trust handling well enough to call it correctly. The gaps are the return payload shape (it references next_since but not the message fields) and any authorization prerequisites.

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 coverage is only 29%, yet the description supplies meaning for essentially every undocumented parameter: since = messages after an id with oldest-first ordering, before = history before an id, neither = latest, kind = chat/progress/system, milestone_id = single-milestone filter, limit = 1-100 default 50. This is well beyond the bare schema, which offers only enums and numeric bounds.

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?

"Read a group's chat" gives a specific verb plus resource and immediately establishes the read-only, group-scoped nature of the tool. It is clearly distinguishable from post_group_message or read_room by the resource name, though it never names a sibling explicitly or contrasts itself with read_room.

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 strong when-to-use guidance for each mode: since for incremental reads with a named polling pattern ("poll with the returned next_since"), before for history, and "neither = the latest" as the default path, plus what each filter selects. It stops short of stating when to prefer this tool over a sibling like read_room or get_group.

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