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

readOnlyHint=true already declares the safety profile, so the bar is lower. The description still adds value by disclosing the shape of the response (summary-level only: uuid, title, hostname, zone, plan, cores, memory, state, tags, labels) and by flagging that IPs and disks are deliberately absent — context the annotation alone does not convey. It says nothing about pagination behavior or result totals, which keeps it short of 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?

Three tight sentences: what the tool returns, how to narrow it, where to go for more detail, plus the endpoint. The most decision-relevant information (resource + returned fields + sibling routing) is front-loaded with no filler.

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 low-complexity, zero-required-param list tool with full schema coverage and a readOnly annotation, this description covers everything an agent needs: scope, filterability, response granularity, and the escape hatch to a detail tool. With no output schema, the inline summary-field list adequately substitutes for a documented return shape.

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 every parameter (tag, label, limit, state, offset, search) is already fully documented, including the subtle `a,b` ANY vs `a:b` ALL tag semantics. The description only restates the filter categories the schema defines, adding no new syntax or default information, so the 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?

It names the resource (cloud servers on the account), enumerates the summary fields returned, and states the filter dimensions, so an agent knows exactly what this call yields. It explicitly contrasts itself with upcloud_get_server ('for IPs and disks') and cites the underlying endpoint GET /1.3/server, making it unambiguously the list operation rather than a detail fetch.

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 gives clear context on when this is the right call (broad enumeration, filterable by state/search/tag/label) and routes the agent to upcloud_get_server when IP and disk detail is needed. It does not spell out when-not to use it or mention other list siblings, but the primary alternative is named with the condition that selects it.

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