start_chat

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

With no annotations, the description carries the full behavioral burden. It usefully discloses the reuse behavior ('existing one is reused' for 1:1) and the creation behavior for groups, but omits permissions/auth needs, what happens if a topic is supplied with a single e-mail, and failure modes.

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?

Two compact sentences, front-loaded with the action and its downstream use, then the branching rule. No filler.

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 two-parameter mutation with an easily inferred result, the description covers the key facts: what it returns and how the mode is chosen. Minor gaps remain around permissions and edge cases (e.g. duplicate emails), but nothing blocks a correct call.

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 goes beyond it by explaining the interaction between 'emails' and 'topic' (one person without topic = 1:1; topic implies a named group). That conditional coupling is not expressed anywhere in the schema.

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+resource ('Start (or reopen) a chat') and explains the resulting artifact: a conversationId consumed by send_message/upload_file. It also disambiguates the two modes (1:1 vs group) so the agent knows exactly which resource is produced.

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?

Clearly positions this as the prerequisite step for send_message and upload_file, which tells the agent when to reach for it. It lacks explicit exclusions or a named alternative (e.g. list_chats for finding existing conversations), keeping it short of a 5.

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