One AI Guide

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

Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds 'evidence-backed objective facts' but does not elaborate on potential side effects, errors, or rate limits. It is consistent with annotations and adds minimal extra transparency.

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, concise sentence that front-loads the primary action and key constraints. No superfluous words or redundant information.

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?

The description explains the purpose and constraints well but does not describe the output structure or format, nor does it mention error cases or edge conditions. Since there is no output schema, this leaves some ambiguity about the expected result.

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 only hints at the format of toolIds ('UUID or canonical slug') but does not name either parameter or explain the 'locale' field. It fails to adequately compensate for the lack of schema-level descriptions.

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 action (compare), the resource (tools), the constraints (2 to 5, approved, by UUID or slug), and the nature of the comparison (evidence-backed objective facts). It effectively differentiates from siblings like get_tool (single tool) and search_tools (discovery).

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 provides clear context on when to use this tool (comparing multiple approved tools when identifiers are known) but does not explicitly mention alternatives or when not to use it. The sibling tools are listed separately, but the description itself does not reference them.

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 the tool read-only, idempotent, and non-destructive, so the description only needs to add context beyond that. It adds the 'published' scoping detail, but it does not disclose behavior for unpublished slugs, locale fallback, or error responses. No contradiction with annotations exists.

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 redundancy. It is appropriately sized for a simple retrieval tool and every word contributes to the meaning.

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?

The schema and annotations cover parameter constraints and safety, but there is no output schema and the description does not describe the returned guide structure, behavioral edge cases, or locale semantics. The definition is adequate for a basic getter but leaves meaningful gaps.

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 compensate for the input schema. It clarifies that slug is the lookup identifier, but it completely omits the optional locale parameter, its meaning, and how it affects the returned guide. This is a significant gap for a two-parameter tool.

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') with a clear resource ('published guide') and identifier ('slug'), making the tool's purpose immediately understandable. It is distinguishable from siblings such as list_guides, get_tool, and get_stack by resource type and retrieval semantics.

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 used when you have a specific guide slug, but it does not explicitly state when to use this versus alternatives like list_guides. No exclusions or alternative routing are provided, so the usage guidance remains inferred rather than explicit.

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, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds the 'public approved' scope, which is meaningful behavioral context about visibility/approval, but it does not disclose error behavior or locale 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 front-loaded sentence with no filler; every word contributes to the basic meaning. It is efficient, though it sacrifices detail that would improve usability.

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?

This is a simple read-only tool with rich annotations, but the description omits the optional locale's role, how stack IDs are discovered, and any return-format information given the absence of an output schema. It is minimally adequate but leaves notable gaps.

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 compensate, but it only references 'stack' without explaining that id is the stack UUID or what the locale parameter controls. The schema's type and enum provide structure but not semantic meaning, leaving locale unexplained.

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 verb ('Get'), resource ('stack'), and qualifier ('public approved'), making the core operation clear. It distinguishes from get_guide and get_tool by resource, though it does not explicitly differentiate itself from sibling list_stacks beyond singular versus plural phrasing.

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 get_stack versus alternatives like list_stacks or search_tools. The description does not mention prerequisites or discovery flows, such as obtaining a stack ID via list_stacks.

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 establish read-only, idempotent, and non-destructive behavior, so the description only needs to add context beyond that. It adds useful behavioral constraints: the tool returns only one entity and only approved tools. It does not describe error responses, but the safety profile is already covered by 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?

The description is one short, front-loaded sentence with no filler or redundant phrasing. Every word contributes to specifying the operation, the resource, and the identifier semantics.

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 simple two-parameter schema and strong annotations, the description is nearly complete for correct invocation. It explains the critical `id` parameter and implies the return is a single tool object, though the effect of the optional `locale` parameter is left implicit. No output schema exists, but the tool's name and 'get one tool' wording sufficiently convey the basic return shape.

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 compensate. It does clarify that `id` accepts a UUID or canonical slug, which is meaningful beyond the raw string schema, but it says nothing about the `locale` parameter. The locale enum values make the intended purpose inferable, but the description still leaves that parameter's semantics unexplained.

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'), a clear resource ('tool'), and the unique qualifiers 'one approved tool' and 'by UUID or canonical slug'. This clearly distinguishes it from siblings like get_guide, get_stack, search_tools, and the list_* tools.

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 should be used when you already have a UUID or canonical slug and need a single approved tool, but it never explicitly states when to prefer search_tools for discovery or compare_tools for comparison. No exclusion criteria or alternative routing is given, so usage guidance is left to inference.

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 the operation read-only, idempotent, and non-destructive. The description adds the filtering behavior (only published guides linked to approved tools), which goes beyond annotations. It omits details like pagination and response shape, but for a safe read operation this is adequate.

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 that packs the verb, resource, and filter criteria with no wasted words. It achieves maximal information density for the purpose it conveys.

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?

The description covers the core resource and filtering rule, which is enough to understand what the tool lists. However, with no output schema and no parameter explanation, the agent is left without details on pagination, locale handling, or the returned structure. This is a moderate gap, not a fatal one.

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 needed to compensate by explaining limit, locale, and offset. It doesn't mention any parameters. While the parameter names are reasonably self-explanatory and the schema provides ranges and enums, the description still leaves a gap for an agent unfamiliar with expected values.

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 ('List'), a target resource ('guides'), and clear qualifiers ('published', 'linked only to approved tools') that make the tool's scope explicit and distinct from sibling tools like get_guide or list_stacks. The purpose is immediately 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?

There is no explicit guidance on when to use this tool vs alternatives such as search_tools or list_stacks. No exclusions or alternative routes are mentioned, so the agent must infer the appropriate use case from the filter conditions alone.

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 readOnly, idempotent, and non-destructive behavior. The description adds that it filters for 'approved' stacks, providing additional behavioral context beyond the 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?

The description is a single, focused sentence with no extraneous information. It is concise and well-structured.

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 no output schema, and the description does not mention what fields the returned stacks contain or provide any details about the response format. This is a significant gap for a listing operation.

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 provides no descriptions for limit, locale, or offset (0% coverage). The description does not explain any of these parameters, leaving the agent to infer their meaning from common conventions.

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 tool's function: listing stacks that are approved, public, or template. This is distinct from siblings like get_stack (retrieving a single stack) or search_tools (searching tools).

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 use case (listing approved public/template stacks) but does not explicitly compare with alternatives or state when to use this versus search_tools or list_guides.

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 goes beyond the annotations by explaining the matching behavior (typo-tolerant, singular/plural, chatbot-aware), which provides additional transparency about how the search operates. The readOnly/idempotent hints are already covered by annotations and no contradictions exist.

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, concise sentence that conveys the core purpose and key features without unnecessary verbosity. It is well-structured and easy to parse.

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 5 parameters and no schema descriptions, the description is not complete enough. It does not explain parameter roles (e.g., what q expects, how limit and offset work, what category filters) or any output/pagination details, leaving significant gaps for correct usage.

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 has no descriptions and the parameter coverage is 0%. The description does not compensate by explaining any of the parameters (q, limit, locale, offset, category), leaving their semantics entirely undocumented.

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 tool's purpose with a specific verb ('Search') and resource ('approved One AI Guide tools'), and it distinguishes itself from sibling tools like get_tool or list_tools by describing the search behavior (typo-tolerant, singular/plural, chatbot-aware).

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 implicitly indicates when to use this tool—when you need to find tools by query rather than fetching a specific tool or listing all. However, it does not explicitly contrast with alternatives or state conditions for use, so it falls short of a perfect score.

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