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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds that results are ranked ('best three', 'why it fits') and include health and install data, which is useful behavioral context. It does not disclose ranking criteria, whether results are cached or fresh, or what happens on an empty match set.

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?

Two sentences, no filler, and the return-shape sentence is dense with useful specifics. The ordering is slightly off: the usage instruction precedes the statement of what the tool actually does, so an agent skimming the first clause learns how to call it before learning what it is.

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?

With an output schema present, the description does not need to enumerate return fields exhaustively, and it still gives a compact summary of the payload. Inputs are well covered by the schema plus annotations, so the remaining omission — ranking methodology and no-match behavior — is minor for a read-only recommendation tool.

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 80%, so the baseline is 3. The description reinforces that the task input should be plain-language intent and that the output includes a client-specific install snippet, which ties the 'client' parameter to a concrete effect. It adds little on the 'limit', 'constraints', or 'response_format' parameters beyond what the enum and property descriptions already say.

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 second sentence states concretely what the tool produces: 'Returns the best three servers, each with why it fits, auth, remote or local, health, and the install snippet for the client.' The opening sentence is phrased as caller instruction ('Describe what the user wants to do in plain words') rather than a verb+resource statement, so the tool's verb is really carried by the title. No differentiation from siblings like search_servers or compare_servers, which is a real gap given seven adjacent tools.

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?

'Describe what the user wants to do in plain words' implicitly signals the natural-language, task-first entry point, which contrasts with keyword-style siblings without naming them. There is no explicit statement of when to prefer this over search_servers or compare_servers, and no guidance on what to do when no server matches.

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