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

No annotations are provided, so the description carries the behavioral burden. It does disclose the essential behavior — one random result with optional narrowing — and 'random line' implies a non-destructive read. But it does not state what happens when filters match nothing, whether repeated calls can repeat lines, or what the returned value looks like. For a very simple tool the core behavior is covered, but edge behavior is left undisclosed.

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?

A single sentence that front-loads the core purpose ('One random line') and appends the scoping info ('optionally narrowed by language and register') behind it. Zero wasted words; every token contributes to an agent's decision to call this tool.

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 tool with only 2 optional parameters, no output schema, and no annotations, the description is nearly adequate: it conveys the operation and the filtering behavior. It is incomplete on the return format (no output schema to fall back on), the source corpus, and the meaning of 'register', which an agent would need to know to invoke it 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 50% — lang is documented as a Base language subtag but register is not. The description adds real semantic value by clarifying that both parameters are optional narrowing filters rather than required inputs. However, it provides no format, allowed values, or meaning for 'register', and compensation for the undocumented register parameter is limited.

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 states the core operation — returning a single random line — with an implicit verb that is recoverable from context. It names the resource ('line') and its defining trait ('random'), which distinguishes it from the sibling tools get_lines, search_lines, and list_collections. However, it never says what corpus/collection the line is drawn from, so an agent cannot tell the source without opening a sibling's schema.

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 phrase 'optionally narrowed by language and register' weakly implies a filtering use case, but there is no explicit statement of when to choose this over get_lines or search_lines, and no exclusion criteria or conditions are given. The agent is left to infer that 'random' is the distinguishing use case on its own.

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