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

Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds valuable context beyond this: results are pre-extracted, require no PDF reading, and are returned in one call, which tells the agent about the tool's effort and completeness characteristics.

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?

Every sentence earns its place: the first names the output, the second explains the benefit and usage context, and the third covers input flexibility. The most important scoping information is front-loaded with no filler or 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?

With a single parameter, rich annotations, and an output schema present, the description is complete for correct invocation. It tells the agent what the tool returns, when to use it, and which input forms are accepted, leaving no critical gap.

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 description coverage is 100%, so the baseline applies. The description restates the accepted input forms ('Accepts an arXiv id or URL, DOI, or Pith Number') but adds little meaning beyond what the schema already documents for arxiv_id.

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 and resource: 'Pith's review of one specific paper, in one call.' It enumerates the exact content returned (verdict, scores, summary, weakest assumption, structured argument), which clearly separates it from sibling tools like get_claims or get_falsifier.

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 explicitly states when to use it: 'Use this for any question about a specific paper' and lists concrete question types. It does not explicitly name sibling alternatives or say when not to use it, so it is clear context without exclusions.

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