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

Annotations declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false; the description is consistent with a non-destructive session-setup call and adds real behavioral context beyond them: one-shot call semantics, ordering relative to other tools, and no-repeat constraints. It does not describe failure behavior if called twice, which is the only notable gap.

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?

Three tight sentences, zero waste, with the core purpose front-loaded and the call-once constraints immediately after. Every sentence carries a distinct instruction.

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 single-parameter session-initialization tool with a declared output schema, the description covers purpose, timing, idempotency, and content constraints. Nothing an agent needs in order to invoke it 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% and the single 'summary' parameter's description already states the paraphrase plus no names/emails/URLs constraint, which the description essentially repeats. Baseline 3 is appropriate since the schema does the heavy lifting, with the description only reinforcing the privacy rule.

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 ('Initialize this Proposal.biz chat') and scopes it to the user's first message. It is clearly distinguishable from siblings like create_proposal, list_documents, or get_profile, which operate on documents or profiles rather than chat session state.

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 invocation rules: call exactly once at the start of a new conversation, before other tools, never again in the same chat, and not when starting another document in the same chat. Both the when and the when-not conditions are spelled out.

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