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

Adds real context beyond the annotations: a human is contacted, the buyer will be emailed, and there is no cost to the buyer — none of which is inferable from readOnlyHint=false / openWorldHint=true. It does not warn that the operation is non-idempotent (repeated calls send repeated requests to a person), which is the one notable omission for a human-in-the-loop tool.

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?

Four tight sentences: what it does, when it is allowed, what it costs, how to use notes. The consent constraint is front-loaded rather than buried, and nothing is repeated from the schema verbatim.

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 14-parameter write-ish tool with no output schema, the description covers the crucial agent-side risks: consent, contact consequences, and cost. What it does not say is what the tool itself returns (a confirmation? a request ID?), though it does imply the actual inventory answer arrives later by email.

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 50% across 14 parameters. The description reinforces the two most consequential required fields (real name, real email, explicit consent) and steers notes toward a listing URL, but seven parameters — condition, min_seats, buyer_phone, budget_max_usd, wheelchair_lift, city, state — carry no description anywhere. Baseline 3 is appropriate; the description compensates partially but not fully.

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 ('send a buyer's bus requirements'), plus the mechanism (a CommercialBuses person searches participating dealer inventory and replies by email). This clearly separates it from read-only siblings like search_buses and get_bus, which the agent can tell apart without opening either schema.

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 an explicit gating condition: 'Use only when the buyer has asked you to, with their real name and email.' It also notes the request is free for the buyer and that a specific listing goes in notes. It stops short of naming an alternative tool for a self-serve search, but the human-routing framing implicitly routes that elsewhere.

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