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

Annotations already declare readOnlyHint=true and idempotentHint=true, and the description enriches this by stating 'PUBLIC metadata only, never corpus rows,' clarifying no API key is required, and disclosing that the question is echoed back with a 300-char limit. It also signals the commercial behavior: this is a free sample that feeds into a paid purchase flow. No contradiction with 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?

Three tight sentences pack all essential information: the free/no-key hook, the exact contents of the preview, the parameter semantics, and the subsequent purchase steps. The emoji and arrow flow make it scannable. No word is wasted; front-loading 'call this now' immediately signals actionability.

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 preview tool with two optional parameters and no output schema, the description fully covers return contents (title, price, sample questions, summary excerpt), access constraints (public metadata, no API key), parameter behavior (slug default, question echo), and the surrounding workflow (pay steps after preview). An agent can invoke this correctly without needing additional context.

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 baseline is 3. The description adds value by explaining slug's default routing behavior ('Defaults to the routed session's listing') and that question is 'echoed back,' which is not fully explicit in the schema. It does not restate the maxLength (already in schema) but covers the behavioral aspect of both parameters.

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 and resource: it delivers a free preview of a data listing containing title, price, up to 3 sample questions, and a summary excerpt. It explicitly distinguishes itself from paid querying by noting 'PUBLIC metadata only, never corpus rows,' and the sibling flow (register → data_session_fund → data_session_query) makes clear it is the pre-purchase taste rather than the actual data access tool.

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?

It gives explicit when-to-use guidance: 'No API key needed — call this now' and frames itself as a 'free taste' before buying. It names the exact alternative flow for paid access: 'register → data_session_fund → data_session_query (sandbox_receipt=true).' It also explains the default routing behavior (routed session's listing or pass slug), covering both invocation modes.

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