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

With no annotations present, the description carries the full burden and does so: it discloses the answer corpus (FAQ + plan catalogue + caller's account), identity-awareness via x-api-key/Authorization header, the read-only guarantee ("never reveals keys or other customers' data, never changes billing"), a per-caller daily cap whose breach returns a non-LLM fallback with FAQ links, and the local STDIO refusal path.

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 purpose and topic list, then the constraints — the ordering is right and essentially every clause carries information an agent needs. It is still a single dense run-on paragraph of prohibitions and edge cases that would scan better as structured clauses, which keeps it off a 5.

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 chat tool with no annotations and no output schema, the description covers sourcing, escalation, identity modes, limits and failure modes — nearly everything an agent needs to call it safely. It never sketches the reply shape (answer text plus a conversation_id to continue), leaving that to be discovered at runtime.

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 both parameters are documented there, including the 10,000-character limit and that conversation_id comes from an earlier reply. The description adds no syntax or usage detail about these two fields, so the schema does the work — baseline 3.

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?

Opens with a specific verb+resource ("Ask the customer support assistant") scoped to THIS service, then enumerates the covered topics (plans, invoices, API keys, rate limits, MCP/REST, data accuracy, owner contact). The scope is unmistakable, but it never names the obvious sibling `ask_agent` or explains how it differs, so an agent facing both must infer the split.

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?

Gives a clear usage context (service/plan/billing/API-key questions) and explicitly enumerates what falls outside its remit — refunds, credits, disputes, lost key without current key, human handoff, security reports — all of which get escalated to the owner with a reference. It also states the STDIO precondition. What's missing is an explicit "use X instead" routing to sibling tools for non-support questions.

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