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

Annotations already signal readOnlyHint and idempotentHint. The description adds behavioral context by specifying that it returns 'ids of theses it supports/refutes' and 'full append-only score history', which explains the nature of the returned data.

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 two sentences plus a tier line, with no wasted words. The core function is stated first, followed by usage guidance, making it efficient and front-loaded.

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 simple read tool with one parameter and an output schema, the description covers what it returns and when to use it. No additional context is needed given the tool's low complexity.

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 provides a clear description for the only parameter (claim_id). The description does not add further parameter details but explains what the tool returns, which indirectly adds context. Schema coverage is 100%, so 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 uses a specific verb ('Fetch') and clearly identifies the resource ('claim by id'). It also lists what additional data is returned (thesis ids, score history), distinguishing it from sibling tools like list_claims or delete_claim.

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 states when to use the tool ('to inspect a claim's evidence, current status, and how its outcome has evolved') and includes tier restrictions. However, it does not explicitly mention alternatives or when not to use it.

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