Diagnose Run Failure

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

Annotations already declare readOnlyHint, idempotentHint, and not destructive. Description adds value by explaining it fetches metadata and per-node results, classifies failure types, and returns recommendations. No contradictions.

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 sentences, front-loaded with purpose, then usage, then output. Every sentence adds value. No wasted words.

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?

Description covers input (runID), when to use, what the tool does (failure classification, recommendations), and output summary. Given complexity and existing output schema, description is complete.

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?

Only one parameter runID. Description adds critical context: use runCounter from start_run/run_status, not UUID from URLs. This guidance goes beyond the schema's description, helping the agent avoid common errors.

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?

Description clearly states it diagnoses failed Coalesce runs, fetches metadata and per-node results, classifies failures, and returns fix suggestions. Distinguishes from sibling run_status by specifying it's for completed failed runs.

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?

Explicitly says when to use (failed runs) and when not (in-progress runs), names alternative tool run_status. Provides context that it works best with completed failed runs.

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