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

No annotations are provided, so the description carries the burden of behavior disclosure. It adds two valuable traits beyond a plain search: prices are rescraped daily (so at most a day old) and the returned `claim_url` is intended for a HUMAN to open in their browser — a clear boundary preventing the agent from trying to follow that URL itself. A fuller disclosure might mention pagination or sort order, but the key behavioral risks are covered.

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 consists of three short, information-dense sentences: purpose and scope in sentence one, data freshness in sentence two, and the human-action requirement in sentence three. There is no fluff; each sentence earns its place and the main verb is front-loaded.

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?

Because there is no output schema, the description should convey what the tool returns. It does state that each offer comes with a `claim_url` for the human to open, which is the most operationally critical part of the response. It does not fully describe the remaining fields of an offer or how results are ordered, so an agent must infer some return details, but this is not a blocker for correct invocation.

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?

All seven parameters have detailed descriptions in the schema, including an enum for `offer_type` and a default for `limit`. The tool description only restates the general filter categories (`RAM, vCPU, price, country and type`) without adding any per-parameter nuances. With schema coverage at 100%, baseline 3 is appropriate.

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 specific verb (`Search`) and resource (`live hosting offers across ~75 providers`) and enumerates the filter dimensions (`RAM, vCPU, price, country and type`). It also mentions the `claim_url` return, which helps an agent understand the tool's purpose at a glance and clearly distinguishes it from the single-offer `get_offer` and the provider-listing `list_providers` siblings.

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 implies the tool is for searching and filtering offers, which is a different use case from retrieving one offer (`get_offer`) or listing providers (`list_providers`). However, it never explicitly says 'use this instead of X when you need Y' or gives any exclusion criteria, leaving the routing decision to inference from the sibling names rather than stated guidance.

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