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

With no annotations, the description carries the full burden and does so well: it discloses the data sources (vast.ai / Clore.ai, identity L0), that values are listing prices rather than transaction prices, that extreme values are not trimmed (so distributions may be fat-tailed), that a snapshot timestamp is included, and that calls are free. The non-additivity warning is a genuine misuse guardrail that no structured field could convey.

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 core resource, then progressively adds the return fields, scope boundaries, and data caveats; every clause carries information that is not available elsewhere. The semicolon-chained phrasing is dense and would read more cleanly as short sentences, but nothing is redundant.

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?

There is no output schema, so the description must explain what comes back, and it does: counts, percentile pricing, platform and region breakdown, and snapshot time. For a zero-parameter read tool with no annotations, the remaining concerns (safety, cost, data provenance, comparability) are all addressed explicitly.

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 no parameters, so there is nothing to disambiguate and the baseline applies. The description correctly avoids inventing pseudo-parameters and instead spends its space on the semantics of the returned fields.

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 names a precise resource (device-level real listing market snapshot) and enumerates exactly what it returns: machine counts per GPU model, P10/median/P90 per-card hourly price, platform and region distribution, and snapshot time. It also explicitly demarcates itself from the sibling cvin_market_price by stating it does not contain model-level quotes, so an agent can route between them without opening either schema.

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?

Usage context is clear: the tool answers 'how many real machines are listed for each GPU model and at what price', scoped to vast.ai / Clore.ai at identity L0. It adds an explicit prohibition against combining its output with model-level quotes, which is stronger than typical guidance. It stops short of a literal 'use this tool when X, use cvin_market_price when Y' formulation, but the exclusion effectively supplies that routing.

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