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

Annotations declare destructiveHint=true, openWorldHint=true and idempotentHint=true, yet the description says nothing about cost, external inference processing, or the mandatory consent gate — the `consentExternalProcessing` const-true parameter implies data leaves the boundary, which an agent must disclose before invoking. It also omits that this is a paid service requiring an idempotency key, a material fact for a mutation-shaped call. No contradiction, but the description adds essentially no behavioral context beyond the annotations.

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?

A single front-loaded sentence with no filler, which is structurally clean. But the brevity comes at the cost of under-specification rather than efficiency — the whole definition is 12 words for a six-parameter, destructive, externally-processed tool.

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?

Given nested required inputs, a consent flag, idempotency key, source-run chaining, no output schema and destructive annotations, the description is far too thin. It says nothing about what the tool returns, that it consumes prior run outputs, or that invocation has cost and data-residency implications.

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 67% and the description supplies zero parameter guidance — no mention of `persona` selection, BATNA discipline, deadline format, `sourceRunIds`/`sourceFields` result chaining, or the 75,000-character combined limit. For a nested schema with a required object plus external-processing consent, that leaves the agent to infer call shape entirely from 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?

The description names two concrete actions (prepare strategy, rehearse objections) and a specific resource domain (supplier negotiation), so an agent can tell it produces negotiation prep rather than contract analysis. It stops short of distinguishing itself from the sibling `negotiation` tool or the `procurement_workflow__*_to_negotiation` family, and never states what artifact comes back.

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?

"Before the meeting" is the only usage cue, implying a pre-meeting timing window, but there is no explicit when-to-use versus `negotiation`, `xclause-risk-scoring`, or the meeting-to-negotiation workflow. No prerequisites, no exclusions, no statement of what a caller should bring versus what the tool generates.

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