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

Annotations only say readOnly/openWorld; the description adds that significant context: $1.00 USDC via x402 charged inside the call, failed calls not billed, one payment with no renewal, free status polling, optional webhook push. It does not explain what the flagged result contains beyond 'a drop in your win rate', but the billing and failure semantics are exactly the kind of detail annotations cannot convey.

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 buyer's question, then scope, then pricing — good ordering with no idle sentences. Slight marketing register ('its real Bazaar rivals') costs a point but doesn't obscure meaning.

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?

With no output schema, the description still tells the agent the deliverable is a win-rate verdict plus a drop flag, where results surface (status URL / webhook), and the billing model. What's missing is the shape of the initial result versus the change alert, but an agent can call this correctly as written.

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 tasks, resource and notify are already documented in-schema. The description only echoes the webhook ('an optional https webhook gets each result') and adds nothing about task phrasing or resource expectations 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?

Names a concrete action and outcome: test your offer against Bazaar rivals via the Machine Buyer Panel, then re-run on model changes for 30 days and flag a win-rate drop. The recurring-monitoring scope implicitly separates it from one-off siblings like check_fair_offer and buyer_panel, but it never names an alternative explicitly.

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?

The 'now + 30 days of re-runs' framing implies this is for ongoing monitoring rather than a single check, and the free status URL / webhook options are mentioned. However, there is no explicit 'use this instead of X when Y', so the agent must infer the choice among siblings.

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