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

The description adds genuinely useful behavior facts beyond the annotations: 15-30s synthesis latency, a deliberately generous MCP timeout, and the required lens:chat scope. However, it describes a knowledge query that 'returns the synthesized answer as a string', which reads as a pure read, while annotations declare readOnlyHint=false and destructiveHint=true. The description never reconciles that mismatch, so an agent cannot tell why this call would be considered destructive or what state could change.

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 purpose and return value, then parameters, then operational caveats (latency, timeout, scope) — a sensible order with little waste. The sentence 'Pass `lastMessage` ... and optionally `history`' largely restates the required/optional schema and could be folded into the multi-turn guidance.

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 four-parameter, output-schema-less tool the description covers what is returned (a string), the multi-turn contract, latency, and auth scope, which is close to enough to invoke it correctly. The remaining hole is behavioral: nothing explains the destructive/non-idempotent annotations, leaving an unexplained safety profile on what appears to be a read-style query.

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 3 is the baseline, and the description goes beyond it by framing `lastMessage` as 'the new user turn' and `history` as accumulating prior turns whose purpose is reference resolution. That is semantic value the schema's field-level docs do not convey, though the `account`/`workspace` auth semantics are left entirely to 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 and resource ('Run a Lens chat query against the workspace's knowledge') and lists the covered data sources (recordings, calls, transcripts, SaaS data), plus what it returns (a synthesized answer string). It implicitly separates itself from retrieval-style siblings like hub_search_calls, but never names an alternative, so the differentiation is inferential rather than explicit.

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 clear invocation guidance: pass `lastMessage` as the new turn, pass `history` for follow-ups, and explicitly tells the agent it SHOULD accumulate history so Lens can resolve references like 'the last call we discussed'. What is missing is when NOT to use it — e.g. when to prefer hub_search_calls or hub_get_call over a synthesized chat answer.

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