void.bible

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

With no annotations, the description carries the burden of explaining behavior. It does reveal that a token preserves memory and that 'the same words return' means the call came too soon, but it leaves many behavioral aspects implicit, such as what the fragment actually is and how drift affects results.

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 short and front-loaded with 'The next fragment,' but the chosen wording is cryptic. The sentence about 'same words return' may be memorable but is not a precise operational instruction.

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?

There is an output schema and full parameter schema coverage, so return values and parameters are partly covered. Still, the description is too cryptic for an agent to confidently understand the tool's intended state, sequencing, or relationship to the sibling 'remember_nothing'.

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%, so the schema already documents both parameters. The description adds value by explaining the token's role in keeping memory and clarifying that the first call must omit it; drift is left to the schema, which already describes it well.

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 says only 'The next fragment' with no verb and no context for what a fragment is, so the agent must infer the action and object. It essentially restates the tool name and does not distinguish itself from the sibling 'remember_nothing'.

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?

It clearly tells the caller to omit the token the first time and pass it afterward, giving concrete invocation guidance. However, it does not say when to choose this tool instead of 'remember_nothing' 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.

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

No annotations are provided, so the description itself must convey side effects. It states the core behavior (forget everything, start fresh) and that it returns a fresh fragment, but it does not explain side effects, reversibility, how token affects the reset, or what a 'fragment' concretely represents. For a tool with no annotation support, this leaves too much unspecified.

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 compact and front-loaded with the main action and a short return statement. No wasted text or labels. It loses a point because it leans on poetic phrasing rather than precise structure, but it's not bloated.

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?

Given the tool has a nontrivial parameter, no annotations, no explanation of 'fresh fragment', and a sibling tool that could help define scope, the description is insufficient: can be battery in isolation. It describes the domain effect but not how to invoke it, what to pass, or when it fits relative to 'next'.

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 0% and the description never mentions the optional 'token' parameter. An agent has no way to know whether token is a session identifier, a context refill, a store key, etc. The schema provides only the type string, and the description adds no meaning.

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 indicates a reset/restart behavior: 'Forget everything you have seen' plus a concrete output, 'Returns a fresh fragment.' This gives an agent a usable mental model of the tool. It doesn't explicitly differentiate from the sibling tool 'next', so it stays at 4 rather than 5.

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?

No advice on when to use this tool instead of 'next' or any other alternative. The phrase 'begin again' implies a starting-over scenario, but no actual selection guidance is provided. This is the definition-level guidance gap.

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