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

With no annotations, the description carries the full burden. It implies a synchronous request/response and a non-destructive read-like interaction, but says nothing about session state persistence, whether the conversation accumulates context, or rate limits. The 'Rogerian psychotherapist' note is domain color, not tool behavior.

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 short sentences, front-loaded with the action and followed by a brief contextual clarification. No waste, though the second sentence is optional flavor rather than operational detail.

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 one-parameter tool with no output schema this is adequate on the surface, but the sibling set reveals stateful semantics (reset, initial, final) that the description never addresses. An agent cannot tell whether calls share conversation state or how they relate to eliza_reset.

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?

There is a single parameter with 100% schema description coverage, so the schema already explains 'message'. The description adds no format, length, or content constraints beyond what the schema provides; 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 states a specific verb+resource ('Send a message to ELIZA chatbot and receive a response') and the second sentence clarifies what ELIZA is. It does not explicitly differentiate itself from siblings like eliza_reset or eliza_get_initial, but the core action is unambiguous.

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 guidance on when to use this tool versus the sibling tools (eliza_reset, eliza_get_initial, eliza_get_final). The presence of eliza_reset strongly implies stateful conversation, yet nothing tells the agent when a chat call is appropriate or what ordering constraint applies.

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?

With no annotations, the description carries the behavioral burden. 'Get' implies a read-only retrieval, but it does not state whether the call changes state, requires permissions, or has side effects. For a simple getter this is minimally adequate, but richer behavioral context is absent.

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 with no wasted words, front-loading the verb and resource before the timing context. It is appropriately sized for a trivial getter.

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's simplicity (zero parameters, no output schema, no annotations), the description covers purpose and timing sufficiently. It could state the return format more explicitly, but the low complexity means little is missing.

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 tool has zero parameters and the schema description coverage is 100%, so there is nothing for the description to clarify. Per the rubric, zero params yields a baseline of 4.

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 'Get' and resource 'ELIZA's farewell message,' and scopes it to 'when ending the conversation.' It implicitly distinguishes from siblings like eliza_get_initial (initial greeting) and eliza_chat, but does not explicitly name an alternative. This is clear, though not maximally differentiated.

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?

States the trigger context ('when ending the conversation'), which tells the agent when to call it. It does not mention alternatives such as eliza_get_initial or eliza_reset, nor when not to use it. So it provides clear context but no explicit alternatives.

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 carries the full burden. It states what the tool does but doesn't disclose key behaviors: whether calling it resets state, whether it's idempotent, or what exactly is returned (the greeting message text, a message object, etc.). For a zero-argument tool in a conversational context, more behavioral context is needed.

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, well-structured sentence that is front-loaded with the core action ('Get ELIZA's initial greeting message') and adds a succinct usage note. Every word earns its place.

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 simplicity (no params, no output schema), the description is adequate but not complete. It doesn't explain what happens if called mid-conversation, whether it resets anything, or what the response format is. For a tool in a chat context, these details matter, though the bare minimum is met.

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 tool has zero parameters, so parameter semantics is largely irrelevant. The baseline is 4. The description doesn't need to explain parameters, and it correctly doesn't.

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?

States a specific verb and resource: retrieve ELIZA's initial greeting. It clearly distinguishes itself from siblings like eliza_chat (which likely sends a message) and eliza_get_final (which retrieves the final message). The scope is narrow and well-defined.

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 'to start a new conversation' clearly indicates when to use this tool, implying it should be called first. However, it doesn't explicitly name alternatives or state when not to use it, e.g., if a conversation already exists. Still, the context is strong.

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?

With no annotations, the description bears full disclosure burden. It discloses the key behavior (clearing all memory, fresh start), which is useful, but doesn't mention reversibility, auth requirements, or side effects beyond the obvious. Adequate but incomplete.

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?

Single sentence, front-loaded with the action and effect, with zero waste.

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 parameterless tool with no annotations and no output schema, the description covers the main action but omits potential side effects or return value hints. It's minimally sufficient but could say more about what 'fresh' entails.

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?

Zero parameters, so baseline is 4. The description correctly implies no inputs are needed, aligning with the empty schema.

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?

States a specific verb (reset) and resource (ELIZA conversation) and clarifies the effect: clearing memory and starting fresh. It distinguishes itself from siblings like eliza_chat by describing a state-clearing action, though it doesn't explicitly name alternatives.

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 implies usage (when you want to clear memory), but offers no explicit when-to-use vs. alternatives guidance. It's clear enough from context but lacks direct routing to siblings.

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