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

Annotations already establish readOnly=true, destructive=false, and a closed-world scope, so the safety profile is covered. The description adds genuinely non-obvious behavioral context that the annotations do not: the result is deterministic, and missing data surfaces as 'unknown' or 'degraded' rather than being silently omitted — which directly affects how an agent should interpret the output.

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 compact sentences with zero filler, and the scope-defining clause leads while the fallback semantics follow. Nothing is repeated from the title or annotations.

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?

An output schema exists, so the absence of return-value documentation is acceptable. However, for a seven-parameter aggregation tool the description leaves the parameter surface and the choice among several overlapping Railway health/status siblings entirely unaddressed, making it only minimally sufficient.

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?

Six of the seven parameters have no schema description, and the description compensates for none of them: it never explains what 'project' expects, what format 'since' takes, what 'environment' filters, or what include_logs, include_metrics, and max_services actually control. With coverage at 14%, the description needed to carry this burden and does not.

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-and-resource combination ('health rollup') and enumerates the domains it covers: services, deployments, and optional recent errors. That is enough to tell it apart from narrow siblings such as railway_deployment_get or railway_logs, though it never names the closest alternative (railway_metrics_summary) explicitly.

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 statement of when to reach for this rollup versus railway_project_status, railway_metrics_summary, railway_incident_diagnosis, or railway_dashboard. The word 'rollup' hints at an aggregate overview, but the agent must infer the selection rule rather than being given it, and no prerequisites are mentioned.

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