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

Goes well beyond readOnlyHint=false by disclosing the side effects that matter: a room is created, join credentials (token + media url) come back, and a call_invite control message is injected into the DM thread — an externally visible effect on the recipient. That is exactly the context an agent needs before triggering a mutating, other-party-visible action.

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?

Front-loaded with the core action and disambiguation first, then side effects, then the optional flag. No filler sentences; every clause carries either identity, exclusion, or outcome information.

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?

Covers initiation, side effects, and the return payload (token + media url) despite there being no output schema, which is the bulk of what an agent needs. Minor gaps remain around failure modes, invite expiry, and whether a call can be upgraded to video after start.

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 'to', 'video', and 'thread_label' are already documented with patterns and defaults. The description's 'Set video:true for video' merely restates the schema's boolean, adding no new semantics such as whether video can be upgraded mid-call.

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 ('Start a 1:1 real-time voice (or video) call with a contact') and immediately disambiguates it from the two lookalike transports, mTALK and mCALL. An agent can distinguish it from mDM_call_answer/mDM_call_end or mTALK_open without opening any 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?

Explicit exclusions ('NOT walkie-talkie mTALK, NOT PSTN mCALL') give a clear when-not, and the mention that the contact 'can answer' implies mDM_call_answer is the counterpart. It stops short of naming mDM_call_answer/mDM_call_end as the lifecycle siblings, so the routing is inferred rather than stated.

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