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

Annotations already declare readOnlyHint, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds genuinely non-derivable behavior: the output is correlational and hypothesis-generating rather than a confirmed root cause, which tells the agent to hedge its conclusions. It does not mention latency, cost, or how many services it fans out across.

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 short sentences, front-loaded with the core capability and the data sources it correlates, with no filler. The terseness is efficient but borders on under-specification for a seven-parameter tool.

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 return structure need not be explained, but with seven parameters at 14% coverage and no routing guidance among a very large sibling set, an agent cannot reliably choose this tool or populate its inputs from the description alone. The hypothesis caveat is the only substantive addition.

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 14% — just context_id is documented — so the description must carry the burden for project, service, since, symptom, environment, and max_services. Instead it says nothing about any of them: not the time format for 'since', not whether 'symptom' is free text, and not what max_services bounds.

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?

States a specific verb and resource combination: a correlated read-only diagnosis spanning deployments, logs, and metrics, which separates it from single-source siblings like railway_logs or railway_metrics_summary. It never explicitly names those siblings or scopes the tool to a Railway project/service incident, so the differentiation is inferable rather than stated.

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 framing as 'incident diagnosis' implies the situation to use it, and 'returns hypotheses — not confirmed root cause' sets expectations about how to treat the result. However, it names no alternatives and gives no when-not guidance, which matters in a sibling list containing railway_health_summary, railway_project_status, ops_incident_rollup, and dozens of source-specific query tools.

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