infra_configure

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

Annotations declare idempotentHint=true and destructiveHint=false; the description adds valuable behavioral context not in annotations: the scope of effect ('for all subsequent tool calls') and the exact return structure ('Dict with current_config, active_preset, and available_presets'). No contradiction with annotations.

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?

Perfectly structured with front-loaded one-line summary, immediate effect statement, and clearly delineated Args/Returns sections. Every sentence earns its place; zero redundancy with schema 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?

Comprehensive for a configuration tool: covers all 4 primary parameters in description (compensating for thinking_level lacking schema description), documents the auth_token in schema, explains return values despite presence of output schema, and addresses idempotent behavior appropriate to a reconfiguration 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?

With 80% schema coverage, baseline is met, but description adds crucial semantics beyond schema: 'takes precedence over preset's default_model' clarifies parameter priority, and 'resolves to a default_model + flash_model pair' explains the preset abstraction. It also documents thinking_level values not described in the schema.

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?

Opens with specific verb 'Reconfigure' + resource 'server' + scope 'at runtime', clearly distinguishing it from sibling 'infra_cache' and content processing tools. The enumerated capabilities (preset, model, thinking level, temperature) precisely define the configuration surface.

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 states 'Changes take effect immediately for all subsequent tool calls', providing critical temporal scope. While it doesn't explicitly name alternatives to avoid, the immediate-effect warning serves as implicit guidance for when to use (runtime adjustments) vs. when not to use (if seeking persistent changes).

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