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

With no annotations, the description carries full burden. It discloses behavioral traits: handling the Random-House-ends-in-2 exception, flagging book-club editions, and returning three items (printing, verdict, detected line). This goes beyond basic purpose to inform the agent of edge cases and output structure.

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?

Two sentences, front-loaded with the action verb 'Decode'. Every sentence adds information: first sentence states purpose and scope, second lists exceptions and outputs. No wasted words.

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 no output schema, the description fully explains the return values: 'the printing, a plain-English verdict, and the detected line.' It covers anomaly handling (Random-House-ends-in-2) and classification (book-club flags). For a single-parameter tool, this is complete and informative.

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 100% with a description already. The description adds value by providing an example ('10 9 8 7 6 5 4 3 2 1') and clarifying that it can include 'First Edition' wording. This helps the agent understand what to pass and the format.

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 action ('Decode a copyright-page number line / printer's key') and the specific purpose ('to determine which printing a book is'). It specifies the input and output, and distinguishes itself from siblings by mentioning specialized handling (Random-House-ends-in-2 exception, book-club edition flags).

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 tells when to use: when you have a number line and/or 'First Edition' wording. It provides clear context about what to paste. However, it does not explicitly mention when not to use or compare with alternatives (e.g., nmlp_identify_first_edition), which would enhance guidance.

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