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

With no annotations provided, the description carries the full burden of behavioral disclosure and executes it well. It explicitly states it never throws, never partially accepts, and clearly distinguishes errors from warnings with illustrative examples. This goes well beyond what the schema or output schema would convey, giving the agent a precise behavioral contract.

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 appropriately sized and front-loaded with the core purpose. It flows logically from the action to the behavioral contract to usage guidance. It could benefit from more explicit structure (e.g., bullets for errors/warnings), but it remains concise and scannable without redundancy.

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?

Despite strong behavioral coverage, the description leaves critical gaps: it does not describe the input spec's structure (what fields a 'calendar spec' requires), nor does it detail the format of the structured errors/warnings (e.g., whether they are objects with codes, messages, etc.). It also does not state whether validation has side effects (unlikely but not clarified). For a tool an agent uses before any other, the lack of input definition is a significant omission that hampers correct invocation.

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?

The input schema has a single parameter 'calendar' that is an untyped object with no defined properties, and schema description coverage is 0%. The description completely fails to compensate: it never explains what a valid calendar spec should contain (fields, data types, nesting) or how to construct the object. The only references to spec internals (leap rule, moon cycle) are examples of warning conditions, not input requirements. An agent has no guidance on how to build the calendar argument.

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 action ('Check a calendar spec and list everything wrong with it'), the resource (calendar spec), and the output (structured errors and warnings). It also explicitly differentiates itself from sibling tools by noting it is 'the only tool that accepts a malformed spec,' making its purpose unmistakable.

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?

Provides explicit when-to-use guidance: 'Use this before any other tool when you have written or edited a spec yourself.' It also implies when not to use (i.e., after validation, other tools handle valid specs) and highlights its unique capability of accepting malformed specs, which directs an agent's tool selection accurately.

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