Diagnose a service

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

The description adds positive behavioral context beyond annotations: it returns aggregated data (configuration, deploys, instances, logs) in a single call. Annotations already declare readOnly, idempotent, non-destructive. Could mention that it may be expensive or rate-limited, but still good.

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: first lists what the tool returns, second provides usage guidance. No unnecessary words; every sentence earns its place. Front-loaded with key purpose.

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?

The description adequately explains the tool's return content (config, deploys, instances, logs) and aligns with parameters. No output schema, so description compensates. Could mention pagination or format details, but sufficient for a diagnostic tool.

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 100% with clear parameter descriptions. The tool description adds minimal extra semantic beyond the schema (e.g., it mentions 'latest deploys' and 'recent error-level logs' which map to deployCount and includeLogs). Baseline 3 is appropriate.

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 clearly states 'One-call triage for a service' and enumerates specific resources: configuration, latest deploys, running instances, error-level logs. It distinguishes itself from sibling tools like render_retrieve_service, render_list_deploys, etc., by explicitly noting it replaces chaining multiple calls.

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 description gives explicit use cases: 'answer is X healthy? or why is X broken?' and advises using it 'instead of chaining retrieve/list/logs calls.' This provides strong guidance, though it does not explicitly list alternatives when only one aspect is needed.

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