Horse Truth Machine Intelligence

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

With no annotations, the description carries the full burden. It states 'Return' implying a read operation, but it does not disclose any side effects, authentication needs, rate limits, or what 'material' means or how changes are determined. This is a significant gap for a tool with no annotation support.

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 a single, front-loaded sentence with no wasted words. It is concise and to the point, though it sacrifices necessary detail for brevity.

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 no annotations, no output schema, and 0% schema description coverage, the description is inadequate. It leaves ambiguous what 'material' means, what the response format is, and how 'limit' behaves. A more complete description is needed for reliable tool 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?

Schema coverage is 0%, so the description must clarify parameters. It clarifies the 'horse' parameter as the target horse, but it does not explain the 'limit' parameter or how it affects results. The description adds partial value but fails to cover all parameters.

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 (Return), a specific resource (Horse Truth change events), and scope (for one horse). It clearly distinguishes from siblings like horse_rankings (rankings) and resolve_horse (resolution), though it doesn't explicitly differentiate from horse_intelligence.

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 the tool is for retrieving change events for a single horse, but it provides no explicit guidance on when to use it versus alternatives, nor does it mention exclusions or prerequisites.

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 full burden of disclosing behavior. It does state that raw provider records are not exposed, which hints at a read operation with data restriction. However, it omits other important behaviors such as authentication requirements, rate limits, side effects, or the shape of the returned intelligence. The single note is minimal and does not sufficiently inform the agent about side effects or permissions.

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 extremely concise, using only two sentences with no filler. It front-loads the core purpose and adds a relevant caveat. While it is under-specified, the structure itself is efficient and clear, earning a high score for conciseness rather than completeness.

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 no output schema and no annotations, the description should explain what 'intelligence' entails and what the return value looks like. It only states that raw records are not exposed, which is a negative constraint but does not describe the positive content of the response. For a single-parameter tool, the description is incomplete for correct invocation and interpretation of results.

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 defines a single required parameter 'horse' as a string, but the description does not explain what this parameter represents (e.g., an ID, name, or alias). Schema description coverage is 0%, so the description must compensate for the missing parameter documentation. It fails to do so, leaving the agent to guess the format and meaning of 'horse'.

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 verb (Return) and resource (Horse Truth derived intelligence for one horse). It is specific about the scope (single horse) and adds a note that raw records are not exposed, which clarifies what is returned. However, it does not differentiate from sibling tools like horse_changes or horse_rankings, so the purpose is clear but not fully contextualized.

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 gives no guidance on when to use this tool versus the sibling tools. It does not mention any conditions, prerequisites, or alternatives. An agent would have to infer from the name alone, which is insufficient for correct selection.

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 full responsibility for behavioral disclosure. It implies a read operation ('Return', 'cache') but does not explicitly state that it is non-destructive, mention prerequisites, rate limits, or side effects.

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 a single, direct sentence with no filler. It is appropriately brief for a simple tool, front-loading the action and resource.

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 one optional parameter and no output schema, the description is thin. It does not explain what 'Horse Truth rankings' are, what format the response takes, or any edge cases, making it insufficient for full understanding.

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%, so the description must explain the meaning of the 'limit' parameter. It does not mention it at all, leaving the agent to infer its purpose from the schema alone.

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 ('Return') and identifies the resource ('current derived Horse Truth rankings') and a source ('already-warmed canonical model cache'). It is clear what the tool does, though it does not differentiate from siblings, which all have distinct names.

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 is given on when to use this tool versus horse_changes, horse_intelligence, or resolve_horse. The description does not mention any conditions, exclusions, or alternatives, leaving the agent without help in selecting 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?

With no annotations, the description must carry the full behavioral burden. It implies a lookup/read operation but does not state whether it is read-only, what happens for ambiguous or unmatched queries, or what the tool returns. The phrase 'resolve ... against profiles' hints at the behavior but leaves the operational details 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?

The description is a single front-loaded sentence with no filler or redundant restating of the tool name. It is lean, though the brevity comes at the cost of omitted behavioral and parameter details scored elsewhere.

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 no annotations, no output schema, and zero parameter documentation, the description is incomplete. It leaves unresolved how the query is interpreted, what a successful resolution looks like, and how this tool differs from the sibling tools.

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 schema description coverage at 0% and no parameter documentation in the schema, the description needed to explain what the query parameter should contain (e.g., name, ID, partial text). The one-sentence description only vaguely references 'horse identity' and never specifies the expected input format or semantics.

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 ('resolve') and resource ('a horse identity against Horse Truth profiles'), so an agent can tell this is an identity-lookup/disambiguation tool. It doesn't explicitly differentiate it from siblings like horse_intelligence, but the focus on identity resolution is distinct enough.

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?

There is no guidance about when to use resolve_horse versus horse_changes, horse_intelligence, or horse_rankings. No exclusions, conditions, or alternatives are mentioned, so the agent must infer the intended use case from the tool name.

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