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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds non-annotation behavioral boundaries: 'MCP never starts checkout' and 'Payment never changes a verdict', which tell the agent there are no purchase or ranking side effects. The 'no tool on this server opens a seal or gives a KEEP' line adds domain-level constraint, diluted only by the opaque vocabulary.

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?

It is short and front-loads 'START HERE', which is good. But the sentences are packed with undefined terms ('seal', 'KEEP', 'scientific contract') and the negative guarantees (checkout, payment, verdicts) are interleaved with the core purpose rather than ordered after it, forcing re-reading.

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?

An output schema exists, so return shape needn't be explained, and the safety profile is carried by annotations. What remains missing is what the 'contract' payload actually contains and what 'seal'/'KEEP' mean in this domain — vocabulary an agent needs to interpret the response but cannot derive from the schema alone.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline of 4 applies. The description correctly implies a single fixed-payload read with no filtering options to select.

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 core sentence 'Exact sold catalogue, with prices read from the site's catalogue, and scientific contract. Lists what is NOT sold' does identify the resource returned, so the purpose is recoverable. But it is wrapped in unexplained jargon ('opens a seal', 'gives a KEEP', 'verdict') and never states a clean verb+resource, so an agent must decode the framing before knowing this is the catalogue/contract lookup.

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?

'START HERE' gives an explicit entry-point ordering, and the description names the alternative for verdicts: 'a verdict is only given by the local Strategy Arena Lab (get_lab_desktop_handoff)'. That is genuine routing, though it does not position this tool against the many other catalogue-ish siblings (list_native_strategies, list_arena_assets, get_pine_converter_contract).

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