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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description does add genuinely useful behavior beyond that: the aggregation set (latest/min/max/average) and the fact that failures or empty measurements yield a 'typed gap' rather than an error. It says nothing about rate limits, time-range constraints, or whether include_series materially changes payload size.

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 short, front-loaded sentences that lead with the resource domain and then the return shape; nothing is padded. The final sentence about include_series duplicates the schema default and is the only sentence that does not earn its place.

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 9-parameter tool with 3 required scoping parameters and near-zero schema descriptions, the description is far too thin to let an agent construct a correct call. An output schema exists, so return values need not be spelled out, but the missing time-window, metric-name, and limit semantics leave real ambiguity.

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 only 11% across 9 parameters, so the description carries the burden and largely fails: since/until formats, the accepted values for the metrics array, limit/pagination meaning, and the project/environment/service scoping are all undocumented. The only parameter it addresses is include_series, and that merely restates the schema default of false.

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?

Names a concrete resource domain (service CPU, memory, network, disk) and what it returns (latest/min/max/average facts), so an agent can tell this is a metrics-fetch tool rather than a logs or status tool. It never explicitly distinguishes itself from siblings like railway_health_summary or railway_service_status, so it stops short of a 5.

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?

There is no when-to-use guidance at all: nothing says when to pick this over railway_health_summary, railway_service_status, or railway_dashboard, nor when not to use it. The metric families imply a monitoring use case, but the agent must infer it.

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