manage_state

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

With no annotations provided, the description carries full burden and does well by explaining the tool's behavioral scope: managing persistent data across requests, supporting CRUD operations, and including a reset function to restore seed data. It doesn't mention permission requirements, rate limits, or error behaviors, but covers the core functionality adequately given the annotation gap.

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?

The description is efficiently structured with a purpose statement followed by action listings with examples. Every sentence serves a clear purpose. It could be slightly more concise by reducing some repetition in the action listings, but the information density is high and well-organized for agent comprehension.

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?

For a complex tool with 10 parameters, no annotations, and no output schema, the description provides substantial context through examples and action explanations. It covers the tool's scope, available operations, and parameter usage patterns. The main gap is lack of information about return values or error conditions, but given the comprehensive examples, it's mostly 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?

Despite 100% schema description coverage, the description adds significant value by providing concrete examples that illustrate how parameters combine for each action. The examples show parameter usage patterns (e.g., action+resource+item_id for get_item, action+resource+data for create_item) that help the agent understand parameter relationships beyond individual schema descriptions.

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 the tool's purpose as managing stateful mock resources with CRUD collections that persist data across requests. It specifies the exact operations available (overview, add_resource, list_items, get_item, create_item, reset) and distinguishes this tool from siblings by focusing on persistent data management rather than logging, mocking, or chaos engineering functions.

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 provides explicit usage guidance by listing all six available actions with clear examples for each. It specifies when to use each action (e.g., 'Use overview to see all resources', 'Use add_resource to create a new resource'), creating a comprehensive decision framework for the agent. The examples serve as concrete when-to-use instructions.

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