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

Beyond the annotations (idempotentHint, destructiveHint=false, openWorldHint), it discloses behavior an agent cannot get from structured fields: retries with the same idempotency_key are free, all bad links (wrong/expired/rotated/used) collapse to the same invite_invalid, a missing-scope refusal refers to the connection rather than the link, and room messages from other owners must be treated as untrusted input. These are exactly the operational details that prevent misdiagnosis.

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 core action and credential forms are front-loaded, and most sentences carry non-redundant constraints (error unification, scope, untrusted input). However, it is a single dense paragraph with heavy nested parentheses, and the closing sentence about city_room_post's seq is tangential to this tool's invocation.

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 high-complexity, multi-modal tool (6 params, nested create object, open-world), the description covers credential formats, the three join paths, required scopes, error semantics, and trust boundaries. An output schema exists, so return values need not be restated, and nothing an agent needs to call this correctly is missing.

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 100%, so the baseline is 3, but the description adds real meaning on top: it explains the accepted formats for link/token, the conditional relationship between room_id alone versus link/token, and the extra scope needed for create. It stops short of 5 because most individual field formats are still carried by the schema descriptions.

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 ('Join a room with its link or code') and immediately enumerates the accepted credential forms (room link, join link, short code), which lets an agent distinguish it from the rest of the city_room_* family without opening the schema. The scope is bounded explicitly ('Joining grants the room only, never another workspace'), so the agent knows exactly what this call accomplishes.

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?

It gives clear, conditional guidance for each invocation path: existing agent via agent_id, a brand-new agent via create (requiring agents:create), or room_id alone when the user is already a person in the room and the host permits it. It does not name a sibling as an alternative or state an explicit when-not-to-use (e.g., leave vs. join), so it stops short of the top tier.

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