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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds value by disclosing the return shape (the full JSON object with fields like dcpi_verdict, composite_score, last_updated) and the free-preview vs. paid-challenge behavior via the mpp_pay/mpp_credential params. It also notes that mpp_pay is 'step 1' and mpp_credential is 'step 2', which is behavioral context beyond the schema. The only minor gap is that it doesn't explicitly state what happens on the free preview (e.g., truncated result), but the description does say 'instead of the free preview' and 'receive the full result' for the paid path, which implies the free path returns a preview. This is strong for a read-only 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?

The description is dense but well-organized: it front-loads the primary use case, gives an example, then lists params and return fields, then closes with exclusions. Every sentence earns its place. It's slightly long (about 120 words) but for a tool with 6 params and a rich return object, this is justified. The structure is logical: use case → example → params → returns → exclusions. A 4 because it's slightly verbose in the return-field listing, but that's arguably necessary for an agent to know what it gets.

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?

The tool has 6 params, an output schema, and complex MPP payment behavior. The description covers the use case, the return shape, the payment flow, and the exclusions. The output schema exists, so the description doesn't need to explain return values in detail, but it does anyway for the key fields. The MPP flow is fully explained (step 1: set mpp_pay=true to get a challenge; step 2: set mpp_credential to pay). Nothing an agent needs to call this correctly is missing. The only thing not covered is the exact free-preview behavior, but that's a minor edge case given the output schema and the description's clarity.

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 all 6 parameters. The description adds value by explaining the market param format (market_slug with examples), clarifying that mpp_pay is a 'price quote' not a charge, and that mpp_credential is a 'Shared Payment Token' for one call. It also explains the relationship between the two MPP params (step 1 and step 2). The description doesn't add much for metric/period/compare_to beyond what the schema says, but the schema already covers those well. Given 100% coverage, a 4 is appropriate for the added MPP context and slug examples.

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 ('get'), a resource ('market intelligence'), and a precise scope: ONE data-center market across 300+ markets. It lists the exact data points returned (vacancy, capacity pricing, supply pipeline, dominant operators, YoY growth) and gives a concrete example with a market slug. It also explicitly distinguishes itself from siblings (rank_markets for multiple markets, get_facility for a single facility), so an agent can tell it apart without opening schemas.

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 opens with 'Use when a user asks about ONE data-center market' and explicitly states what NOT to use it for: 'Do NOT use to rank multiple markets (use rank_markets) or for a single facility (use get_facility).' This is explicit when/when-not guidance with named alternatives, which is exactly what the dimension asks for.

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