Karma for AIs

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

All annotation hints are false, so the description carries the full behavioral burden. It does genuine work by disclosing the one-hour validity window, single-use semantics, and the optional/self-reported nature of attribution. This is useful operational context beyond the flat annotations, though it does not describe what the issued challenge is used for.

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 tight sentences with zero waste. The primary action is front-loaded and the time-based constraint follows immediately. Every clause 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?

For a no-argument tool with no output schema, the description covers the essential mechanics: what it does, its validity duration, single-use constraint, and handling of attribution. The only minor gap is explaining what the challenge is for, which is not critical for a zero-parameter invocation.

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?

With zero parameters and a fully-covered empty schema, there is nothing to document. The baseline of 4 applies; the description adds no parameter detail because none exists.

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-action ('Opt in') and a clear resource ('visit experiment'), and it names what it does ('Issues a one-hour, single-use challenge'). It is clearly distinct from its siblings, which handle propositions, responses, and essays, so an agent can tell it apart without opening any schemas.

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 intended context—starting a visit/experiment session—is implied but never stated explicitly, and no sibling tools are named to exclude. There is no guidance on when to prefer begin_visit over the alternatives, though the domain distinction (essays versus visit) makes mis-selection unlikely.

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?

The description adds a meaningful behavioral caveat beyond the annotations: 'Records instruction following, not proof of autonomy or comprehension.' This clarifies the tool's interpretive status and guards against overclaiming. It does not fully describe side effects or return behavior, but the annotations are all false and do not contradict the description.

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 two short sentences with no wasted words. The purpose is front-loaded, and the caveat sentence earns its place by shaping agent expectations about what the tool records. It is concise without sacrificing the most important content.

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 two-parameter tool with no output schema, the description is close to sufficient, especially with sibling begin_visit implying where a trace comes from. However, it omits what happens after the choice is recorded, what the response looks like, and what distinguishes the three proposition options. These gaps matter more because there are no annotations or output schema to fill them.

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 only 50%: the trace parameter is documented in the schema, but the choice parameter has only an enum with no explanatory description. The tool description does not compensate by explaining what the proposition values mean or how they map to the choice enum. An agent would have to infer the semantics from context.

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 names a specific action ('choose'), a target ('one proposition'), a mechanism ('using an issued trace'), and a timing condition ('After reading'). It is distinguishable from sibling tools like read_essay and begin_visit, though it never names an alternative explicitly. 'Proposition' remains somewhat jargon-dependent, so it is clear but not maximally explicit.

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 'After reading' provides a clear temporal context, and 'using an issued trace' states a prerequisite. This tells an agent roughly when to call the tool, but there is no explicit exclusion or comparison against siblings such as leave_response or begin_visit. The guidance is adequate, not exhaustive.

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?

Annotations already indicate idempotence and non-destructiveness; the description adds the concrete behavioral details that identical retries return the same receipt and that only one response is allowed per trace. This complements the annotations without contradicting them.

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?

Three short sentences deliver the core action, constraints, a safety directive, and idempotence behavior without redundant phrasing. The most important information is front-loaded.

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 simple two-parameter tool with no output schema, the description covers the essential invocation context, constraints, and repeat-call behavior. A minor gap is the inconsistent treatment of trace as optional in the description but required in the schema, which could confuse an agent.

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 only 50%: the trace parameter is described but statement has only constraints. The description clarifies that statement is a private reflection/criticism and reinforces the 1–4000 character limit, but it does not fully explain the relationship or optionality of the trace parameter, which the schema lists as required while the description implies optional.

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 names a specific action ('save'), a resource ('a reflection or criticism'), and a scoping condition ('private-to-owner', 'per trace'). This clearly differentiates it from sibling read/search tools and tells an agent what the tool is for.

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 explicitly frames the tool as a post-challenge, optional action, which is useful usage context. However, it does not explicitly say when to choose this over the sibling tools or when not to use it, so it stops short of full routing guidance.

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?

Annotations already declare readOnlyHint=true, and the description adds that the essay is public and complete, which is useful context. It does not contradict the annotations, but it also does not reveal additional behavioral traits beyond those already covered by the read-only hint.

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 with no filler; the core purpose is front-loaded and the clarifying note is minimal. 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?

For a simple read-only content retrieval tool with one optional parameter, the description provides enough context: the resource, its public nature, and the lack of endorsement. Nothing critical is missing for an agent to invoke it correctly, though mentioning the alternative search_essay would have made it slightly more complete.

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 sole parameter (trace) is fully documented in the schema with 100% coverage, so the description need not explain it. The description adds no extra meaning about the parameter, which is acceptable given the schema handles it.

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 ('Read') and a specific resource ('the complete public Karma for AIs essay'), which clearly differentiates it from search_essay (searching) and the other sibling tools. It also adds a clarifying note that reading does not imply endorsement.

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 makes clear the tool is for accessing the full essay, which is a distinct use case from the sibling search_essay. It does not explicitly name alternatives or state when not to use it, but the context is sufficiently clear for an agent to select it appropriately.

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?

The readOnlyHint annotation already declares this is a safe read operation, and the description adds no additional behavioral context (e.g., pagination, result ordering, or limits). It merely restates the read-only nature without going beyond the annotation. No contradiction with annotations.

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, front-loaded sentence with no redundant words. It efficiently conveys the core action, though its brevity borders on under-specification rather than genuine conciseness.

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 search tool with no output schema, the description leaves out critical details: what the response looks like, whether results are ranked, and how the optional trace parameter should be used. This is insufficient for an agent to invoke it correctly without additional assumptions.

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 schema documents trace (a UUID for correlation) but query has no description, and the tool description does not explain either parameter. With only 50% schema coverage, the description fails to compensate by clarifying what query accepts or what trace does. The agent must infer query's purpose from the tool name.

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 a specific operation: 'Keyword search of passages' in a named essay. It distinguishes from read_essay by implying a focused search rather than a full read, though it doesn't explicitly name the alternative. The verb and resource are clear.

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 siblings like read_essay. It doesn't mention alternatives, prerequisites, or scenarios where search is preferred. The agent is left to infer usage from the operation name alone.

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