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

Discloses behavior far beyond the annotations: the reply is sent to a model provider and incurs usage cost, keyword-rule fallback with a 'source' discriminator, the reply text is not retained while analytics records the decision, 404 not_released semantics, required pcn:routing:read scope, and 403 for unclaimed sandbox workspaces. This also explains why readOnlyHint=false despite the 'read' framing.

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?

Purpose and outcome taxonomy are front-loaded in the first sentence, and every subsequent sentence carries distinct information (fallback, cost, retention, error codes, auth). It is long and densely packed into run-on sentences, but almost no clause is redundant.

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?

There is no output schema, so the description enumerates the return fields (label, confidence, option probabilities, counter_price) itself, and it covers auth prerequisites, billing side effects, privacy/retention, and the 404/403 failure modes. An agent has everything needed to call it and interpret the result.

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 description coverage is 100%, so all three parameters are already documented, including the subtle 'counter equal to quoted price is not read as a counter price' rule. The description only restates 'with quoted_price and currency when known' and mentions counter_price output, adding little syntax or format meaning beyond the schema. Baseline 3 applies.

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 (read) plus resource (buyer's reply to a quote) and enumerates the exact classification outcomes the tool produces (accept, too_high, counter, question, decline). The line 'This call does not accept a deal or change a price' draws a clear boundary against mutation siblings such as accept_counter or pricing_conversation.

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 concrete invocation context ('Send text, with quoted_price and currency when known') and an explicit when-not ('does not accept a deal or change a price'), which implicitly routes the agent elsewhere. It stops short of naming the alternative tool to use instead of accepting a deal, so it is clear but not fully routing.

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