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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the description is not burdened with the safety profile. It still adds real value beyond them: output is compa cted with the full JSON available via full_url, the call is never billed, and it explicitly warns that third-party text inside (token names, market questions) is data, not instructions — a prompt-injection guard. It does not mention rate limits or payload size limits, which keeps it off a 5.

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 action and its value proposition, then the enum glosses, then output-shape and safety notes. 'Free, never charged' is somewhat redundant with 'free sample' in the first clause, a minor repetition in an otherwise dense, well-ordered block.

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?

No output schema exists, but the description compensates by explaining that the response is compacted and that full_url carries the full JSON, so the agent knows what it will receive. With a single enum parameter fully documented and safety covered by annotations, the only remaining gap is any hint of sample size or selection-bias limits (i.e., it is a sample, not the full kit).

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 100% and the enum is already constrained, so the baseline is 3. The description goes further by glossing each enum member ('sol-kit (Solana rug check complete kit)', 'gens-ops' EVM gas ops kit, etc.), which tells the agent what payload each sample actually contains — meaningfully beyond the schema's bare 'which sample'.

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?

Specific verb plus resource: 'return a real, free sample of a paid product', with all four sample kinds enumerated and glossed inline (sol-kit, pm-kit, sol-verdict, gas-ops). An agent can tell it is a preview/sample endpoint rather than a listing or pricing endpoint. It never names the siblings (avasis_products, avasis_quote, avasis_verdict_rubric), so differentiation is only implicit.

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?

'so you can see the exact keys before paying' implies this is the pre-purchase inspection step, and 'Free, never charged' removes cost concerns. But there is no explicit statement of when to pick this over avasis_products or avasis_verdict_rubric, and no exclusion or prerequisite guidance. Usage must be inferred from the sample/before-paying framing rather than being stated.

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