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

Annotations already declare read-only, idempotent, non-destructive behavior, and the description adds real value beyond them: a non-contract variant returns null, and the returned filter config deliberately omits whether unreachable types are hidden, pointing the agent at the description field instead.

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?

Front-loaded with what is read and what it returns, then moves to caveats and prerequisites. Slightly wordy around 'The description states it, so read it there', but every sentence carries substantive information.

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?

An output schema exists, yet the description still covers the null case for non-contract variants and the one field the return does not include, plus the input prerequisites and the PublishContract relationship. Enough for an agent to call and interpret this correctly.

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 0%, so the schema gives no parameter meaning; the description partially compensates by mapping the two parameters to 'the graph ID and the contract variant name'. It adds no format, naming conventions, or error semantics for those parameters.

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?

Names a specific verb+resource (read the filter configuration of a contract variant) and enumerates exactly what is returned: included tags, excluded tags, source variant, and description. It also defines a contract variant, so the agent can distinguish this from GetVariantDetails and GetGraphSchema.

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?

Gives clear context for use ('the same read that rover contract describe performs') and an explicit downstream condition ('read it there before you update a contract with PublishContract'). It does not compare against an alternative read tool, but the when-to-use is unambiguous.

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