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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: it discloses the data source (benchmark_cache + Stratalize composites), the freshness condition ('when fresh'), the fallback behavior ('or guidance to load intelligence in Stratalize'), and the pricing ($0.10 USDC per call). This goes beyond the annotations without contradicting them.

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?

The description is compact and front-loaded with the primary use case ('Use when a CFO or procurement lead needs org-specific vendor pricing vs market before renewal or negotiation'). The output fields, example, source, and pricing are packed efficiently into three sentences. It loses one point because the pricing and source details, while useful, are somewhat dense and could be structured more cleanly.

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 read-only benchmark tool with 100% schema coverage and no output schema, the description is quite complete. It covers the trigger condition, the output fields, the data source, the freshness fallback, and the cost. The only minor gap is that it doesn't explicitly state what 'position_label' means or how the negotiation tactics are delivered, but the example and output field list provide enough context for an agent to invoke it correctly.

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 the schema already documents both parameters (vendor_name and mcp_client_source). The description adds context for vendor_name via the example 'HubSpot, QuickBooks, Salesforce' and implies the vendor_name is the key input, but it doesn't add meaning beyond the schema for mcp_client_source. Baseline 3 is appropriate since the schema carries the parameter documentation burden.

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 states a specific verb ('benchmark'), a resource ('vendor pricing'), and a clear scope ('market before renewal or negotiation'). It also names the output fields (market_low, market_median, market_high, position_label, negotiation tactics, estimated_savings_monthly), which distinguishes it from generic benchmark siblings. The example (Salesforce median ~$8,400/mo) further clarifies the tool's purpose.

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 description explicitly states when to use the tool: 'when a CFO or procurement lead needs org-specific vendor pricing vs market before renewal or negotiation.' It also implies the alternative path: 'or guidance to load intelligence in Stratalize' when the benchmark cache is not fresh. This gives an agent clear decision criteria for selecting this tool over the many sibling benchmark tools.

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