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

Annotations already establish readOnlyHint=true, so safety is covered and the description is not contradicting it. It adds real context that results are annotated with last-probe status and come from the official registry, but says nothing about result volume, pagination, or registry staleness.

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, zero filler, with the what/where front-loaded and the usage hint trailing. Nothing repeats the schema or could be deleted without loss.

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 no output schema, the description carries the return-value burden and does so at a high level by naming the per-server probe status. Combined with the live_only schema hint it is nearly sufficient, though it does not describe ordering, volume, or the shape of a result entry.

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 coverage is 50%: live_only is documented in the schema, but the required 'query' parameter has no schema description at all. The description compensates by stating the query matches against name or description, which is genuine semantic value the schema lacks.

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?

Specific verb (search) plus resource (remote MCP servers) with the source scoped to 'the official registry' and the added detail that each result carries its latest probe status. This is far more than a restated name. It stops short of explicitly differentiating itself from check_server, which an agent could plausibly confuse with discovery.

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?

'Use to pick a server that is actually up' implies the intended moment of use but names no alternative and states no exclusions. Nothing tells the agent when to prefer check_server over find_servers, so routing is left to inference.

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