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

Annotations only say non-readOnly, non-destructive, non-openWorld. The description adds materially more: the requester is always a member, `private` bounds visibility to the listed people versus workspace-wide, nothing carries over from the originating conversation, and the call may return a needs_confirmation envelope requiring a human pause. That is the kind of behavioral detail an agent cannot infer from the annotations or schema.

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?

A single dense paragraph with no filler and the core definition front-loaded before the operational rules. It runs long and packs multiple distinct rules into individual sentences, so an agent must read carefully, but every clause earns its place and nothing is repeated.

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 creation tool with no output schema, the description covers the gaps that matter: what gets created, who is included, visibility semantics, the confirmation round-trip, and the fact that the returned `ref` should be pasted back to link the room. Remaining params are fully documented in the schema, so nothing an agent needs 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 baseline is 3, but the description genuinely enriches key params: `people` are workspace members identified by name or email, `private` flips visibility from workspace-wide to members-only, and `opening` is framed as the room's purpose plus a concrete next step written for everyone. `folderId` and `workspace` are left to the schema, which handles them adequately.

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 ('Creates a room') and immediately defines the resource in domain terms ('a shared space where people work together with you, and the person asking is always in it'), which tells an agent what the object actually is, not just its name. It also names the sibling rooms_list as the pre-check, so it is distinguishable from the other rooms_* tools in the same breath.

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?

Explicit routing: 'Check rooms_list first so you don't make one that already exists.' Explicit continuation rule: when the room continues this conversation, put everything needed into `opening` because nothing else carries over. Explicit confirmation protocol: on needs_confirmation, state what you're making and wait. Both when-to-use and the alternative are spelled out.

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