StackResolve

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

With no annotations provided, the description carries the full burden of disclosing behavioral traits. It only says 'Audit a product for agent-readiness,' which implies a read-only analysis but does not explicitly state side effects, permission requirements, or what the tool actually does (e.g., checks documentation, API quality, or something else). It provides minimal behavioral 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 extremely short, which is not necessarily conciseness but under-specification. It front-loads the core purpose, but it omits essential details about parameter usage, expected outcomes, and operational behavior. The brevity reduces its usefulness rather than enhancing it.

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 tool has one required parameter, no output schema, no annotations, and a description that provides no additional context. The definition is far from complete: it does not clarify what the domain should be, what the audit will return, or what 'agent-readiness' means in practice. An agent using this tool without further information would likely fail to invoke it correctly.

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 describes a single required parameter 'domain' as a string, but there is zero description coverage (0%). The description does not explain what 'domain' refers to (e.g., a website URL, product name, or unique ID). Since the schema provides no semantics and the description adds none, agents have no basis for correctly populating the parameter.

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: auditing a product for agent-readiness. It identifies a specific verb (audit) and resource (product), and it is distinct from sibling tools that focus on comparison, pricing, or company research. However, it does not elaborate on what 'audit' entails or what aspects of agent-readiness are evaluated, so it stops short of full clarity.

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 no context on when to use this tool versus alternatives. It does not mention any prerequisites, typical scenarios, or exclusions. An agent has to infer that audit is intended for assessing a product's agent-readiness but receives no guidance on when it would be preferable to research_company, get_profile, or find_tools_for_task.

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 behavioral disclosure. It only states the purpose and fields covered, but doesn't explain behavior such as how it handles missing domains, whether results are aggregated, any authentication requirements, or the structure of the output. For a comparison tool, more context on the side-by-side format (e.g., column/row layout, normalization, error behavior) 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?

The description is a single sentence with no filler. It front-loads the core purpose ('Structured side-by-side') and immediately lists the relevant field categories. Every word earns its place; it is concise and scannable.

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 two parameters, no output schema, and no annotations, the description is too sparse. It omits any explanation of the 'domains' input, how output is structured, error handling, or edge cases. An agent cannot reliably invoke this tool correctly with only this description, even though the schema lists required and optional fields.

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 0% description coverage, so the description must explain both parameters. It lists potential field values (description, products, etc.) which hints at the 'fields' parameter, but the 'domains' parameter is not explained at all. No format, constraints, or default behaviors are conveyed. The description adds minimal value beyond the raw 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?

The description clearly states the tool compares companies side-by-side in a structured format and lists the fields covered (description, products, categories, funding, technology). This distinguishes it from single-company tools like get_company or research_company, though it doesn't explicitly name the alternative. The verb, resource, and scope 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 is given on when to use this tool versus siblings. The description implies comparison of multiple companies, but there is no explicit statement of when to choose this over research_company, find_competitors, or get_company. An agent would have to infer from the tool name alone, which is insufficient.

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, but it only states the basic operation. It does not disclose whether the comparison is read-only, what data it returns, whether any side effects or permissions are involved, or edge-case behavior such as invalid slugs.

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 four-word sentence with no filler, and the core action is front-loaded. It earns its place, though it is so terse that it sacrifices explanatory depth.

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 the input contract is reasonably clear, but with no output schema and no annotations the agent is left to guess what 'compare' actually returns and how to interpret the result. Basic invocation is possible, but the definition is not fully 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 schema has a single required 'slugs' array of strings with no property descriptions, and the description adds the minimal clarification that these are product identifiers used for comparison. This is enough for a very simple parameter, but no constraints, format, or examples are provided.

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 ('compare') and resource ('products') and identifies the input key ('slug'), which sets it apart from the sibling compare_companies. It is clear enough to know what operation is performed, though it doesn't specify what aspects of products are compared or what the result looks like.

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 get_pricing, get_company, or compare_companies. The only hint is the tool name and the phrase 'by slug'; there is no explicit context, condition, or exclusion to route an agent.

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 provided, the description carries the burden of disclosing behavior. It adds useful context by noting the data comes from 'live research' and is 'returned as structured rows,' implying a read-oriented, potentially slower operation. However, it does not describe failure modes, rate limits, latency implications, or what happens when no competitors are found.

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, well-structured sentence with no filler. It front-loads the core purpose and follows with the useful behavioral details of live research and structured rows.

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 tool has no output schema and minimal parameter documentation, so the description must provide more complete invocation context. It omits the input format for domain, the meaning of limit, and any relationship to sibling tools, leaving the agent to guess important details.

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 undocumented parameters domain and limit. It only loosely maps 'for a company' to the domain parameter and says nothing about the semantics of limit, such as whether it caps row count, defaults, or ordering.

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 the tool returns 'real competitors and alternatives for a company,' which clearly identifies the resource and expected output. It uses 'extracted from live research' and 'returned as structured rows' to describe the action, but lacks an explicit verb like 'find' and does not distinguish it from sibling tools like research_company or compare_companies.

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 explicit guidance about when to use this tool versus alternatives such as research_company, compare_companies, or get_company. There are no usage conditions, exclusions, or hints about when to prefer one tool over another.

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 provided, the description must carry the full burden of disclosing behavior. It only says 'Rank' without revealing what the ranking is based on, whether it returns a list, any ordering criteria, or side effects. It also does not mention any requirements or limitations. This is inadequate for a tool with no structured metadata.

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 short sentence, which is not overly verbose, but it is under-specified rather than concise. It lacks essential details that would make it informative. The structure is not front-loaded with key constraints or context; it merely states the action.

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 one parameter, no output schema, and no annotations, the description is the only source of context. It provides almost no information about the tool's behavior, return value, or usage constraints. An agent would not be able to call this tool correctly based solely on this description.

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% and there is only one parameter, 'task', which has no description in the schema. The description does not clarify what format 'task' should take, what kind of input is expected, or how it influences the ranking. With no compensation from the description, the parameter semantics are entirely opaque.

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 action ('Rank') and a resource ('software an agent should use for a task'), which conveys the basic purpose. However, the resource is vague ('software' could mean tools, packages, or something else) and it does not differentiate from sibling tools like search_tools or how_to, which also relate to finding tools. It is not a tautology, but it lacks the specificity needed to distinguish this tool from closely related ones.

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 no guidance on when to use this tool versus alternatives. There is no mention of scenarios, exclusions, or comparisons to sibling tools such as search_tools or resolve. Agents are left to infer use cases, which is a significant gap.

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 of behavioral disclosure. It states what is generated, but not whether this triggers network calls, writes files, requires authentication, or how outputs are returned. The absence of side-effect or prerequisite information leaves an agent uncertain about what invoking this tool will do.

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, compact sentence that lists the key artifacts and the source format. It is front-loaded with the central purpose and avoids redundancy, though the opening phrase 'Make a product agent-native' is slightly jargon-heavy.

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 multi-output behavior, two parameters, zero schema coverage, no annotations, and no output schema, the description does not provide enough context. An agent cannot tell exactly what it must pass, what the generated artifacts look like, or what the tool actually returns after generation.

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 both 'domain' and 'openapiUrl'. It only hints that an OpenAPI source is relevant, without explaining what 'domain' means, where 'openapiUrl' is resolved from, or which parameter takes precedence when both are supplied. This is insufficient for a tool with two undocumented 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 names a clear action ('generate') and a distinct resource: product agent interfaces built from an OpenAPI document. It enumerates the concrete outputs (MCP server, CLI, llms.txt, install snippets), which clearly separates this generator tool from the research/registry analysis tools in the sibling list.

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 it should be used when a product's OpenAPI should be turned into agent-facing artifacts, but it never states explicit conditions for use or warns when not to use it. No alternative tools are referenced, so an agent must infer the appropriate context.

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 provided, the description carries the full burden of behavioral disclosure, but it says nothing about mutability, permissions, errors, data source, or return behavior. 'Structured company record' does not even explicitly state that the tool returns or retrieves data.

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, but this is under-specification rather than deliberate conciseness. It contains no useful structure or detail beyond a noun phrase.

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 output schema, no annotations, and overlapping sibling tools such as get_profile and research_company, a three-word description is insufficient for an agent to select and invoke this tool confidently. It does not explain what data is returned or what distinguishes this lookup from nearby alternatives.

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 does not mention the required 'domain' parameter or clarify what values it accepts. The schema only states it is a string, so the agent gets no added meaning from the description.

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 is a noun phrase, 'Structured company record,' which essentially restates the tool name without a verb or explicit action. It does not differentiate get_company from siblings like research_company, get_profile, or compare_companies.

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 about when to use this tool versus related tools. The description provides no exclusions, prerequisites, or alternatives, leaving the agent to infer the context from the tool name 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?

With no annotations, the description carries the full burden of behavioral disclosure, but 'Normalized pricing' reveals nothing about side effects, read-only behavior, data transformation, or output characteristics. The agent has no idea what normalized means or what happens when the tool is invoked.

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 only two words, which is under-specification rather than effective conciseness. It omits essential information and provides no structure or front-loaded clarity.

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 required parameter, no output schema, and no annotations, the description is completely inadequate. The agent lacks even the basic context needed to invoke the tool correctly or interpret its 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?

Schema description coverage is 0% and the description does not mention the 'domain' parameter at all. The agent receives no explanation of what domain represents, its format, or its 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 'Normalized pricing' is a noun phrase with no explicit verb or action, making it unclear what the tool actually does. It vaguely suggests retrieving pricing data but does not clearly state the resource or how it relates to the 'domain' parameter. It borders on tautology with the tool name.

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 on when to use this tool versus alternatives like get_usage, get_company, or get_profile. No context about typical use cases, prerequisites, or exclusions is provided.

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?

There are no annotations, so the description carries the full burden for behavioral disclosure. It indicates the profile contents but does not explicitly state that this is a safe read-only operation, whether any special authentication is needed, or how errors such as 'slug not found' behave.

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 compact line that front-loads the core resource and adds a concise parenthetical of key contents. Every word earns its place, though it is arguably a noun phrase rather than a complete 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?

For a tool with no output schema and no annotations, the description leaves important context missing: how to resolve the slug, what the response looks like, and how this profile differs from related registry tools. The listed components give a hint but are not sufficient for robust 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 description coverage is 0%, and the description never mentions the slug parameter, what it means, or how to obtain a valid value. With one required parameter and no compensation in the description, an agent cannot confidently construct a correct call.

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 identifies the resource as a 'full registry profile' and lists its main contents (AgentReady Score, capabilities, sources), so an agent knows what it returns. It is not a pure tautology because the parenthetical adds concrete detail. It does not strongly differentiate from siblings like get_company, but the resource 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?

No guidance is given about when to use get_profile versus sibling tools such as get_company or list_registry. The description does not state prerequisites, exclusions, or a preferred context, leaving the decision entirely to the agent's 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It does disclose that the operation is read-only and scoped to the current billing period, which are useful safety cues. However, it does not clarify what 'usage' encompasses—such as calls, cost, tokens, or time—or what the returned data looks like.

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 compact sentence with no filler. Every word adds information: the scope ('this billing period') and the safety property ('read-only') are both included immediately.

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 zero-parameter read-only getter, the description is minimally viable: an agent can safely invoke it based on the provided text. However, there is no output schema and no explanation of what 'usage' includes or how it is returned, leaving an agent uncertain about how to interpret the 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?

The tool has zero parameters, so the description has no parameter semantics to clarify. Per the baseline for no-parameter tools, this is sufficient.

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 identifies the resource as 'your usage this billing period' and marks it read-only, which distinguishes it from related getters like get_pricing and get_profile. However, it uses the noun phrase 'Your usage' rather than an explicit verb such as 'retrieves' or 'returns', so the action is implied rather than stated.

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 no guidance on when to use this tool versus siblings such as get_pricing, get_profile, or audit. 'Read-only' describes the nature of the operation but does not help an agent decide between available 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?

The description discloses the tool's behavior thoroughly: it composes live web research, the tool resolver, and a synthesis pass, and it enumerates the exact output structure ({ approach, recommendedTools, steps, gotchas, deprecated, sources, asOf }). This transparency exceeds typical descriptions and establishes clear expectations for the agent.

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 concise, with the key usage instruction ('BEFORE building something') front-loaded. It is split into two clear sentences and avoids unnecessary jargon or fluff. It could be slightly more streamlined, but it remains well-structured and scannable.

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 tool's core purpose, the high-level process, and the output format. For a single-parameter tool, it is fairly complete. Minor omissions include no mention of error handling or behavior on invalid input, but these are not critical for typical use.

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 only one parameter, 'task', but the schema provides no description, and the tool description only refers to it as 'a task' without detailing type, format, or examples. Since schema coverage is 0%, the description fails to compensate by explaining the parameter's intended value, leaving the agent to infer its 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 states the tool's purpose: to return the current, date-stamped, cited, tool-aware way to perform a task. It also provides the context (before building) and the rationale (to avoid training-cutoff memory). This is unambiguous and directly 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?

The description explicitly instructs to call this tool 'BEFORE building something', giving a concrete trigger for usage. It also explains the benefit (using today's best practice). However, it does not mention any alternatives or conditions when not to use it, so it falls slightly short of fully covering usage guidelines.

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 burden of behavioral disclosure. It only mentions the default sort order, but nothing about how limit, category, or minScore affect results, pagination, or return format. The behavior is largely undefined.

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 sentence with no wasted words. It is concise and front-loaded with the action and sorting. However, its brevity is a result of under-specification rather than efficient thoroughness.

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 three optional parameters, no annotations, and no output schema, the description is drastically incomplete. It omits effect of parameters, expected output, and any edge cases, making it insufficient for an agent to use correctly.

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 adds no meaning to any of the three parameters (limit, category, minScore). The schema only provides types, so the agent has no idea what these parameters do or how to use them.

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 lists the registry, with a specific sort order (highest AgentReady Score first). It conveys a unique purpose, though it doesn't explicitly differentiate from search_tools or find_tools_for_task, which may also return registry entries.

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 alternatives like search_tools or find_tools_for_task. There are no conditions, exclusions, or context provided, leaving the agent to infer the appropriate use case.

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 disclosure burden. 'Grounded, cited answer' hints that the output includes citations and is sourced, but it omits how sources are selected, whether external web access is involved, failure behavior, or output shape. This is more informative than a tautology but still largely under-discloses.

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 repetition. It is efficient, though it sacrifices substance 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?

For a likely complex research tool with two undocumented parameters, no annotations, and no output schema, this description is too thin. It does not explain how to specify the company, what form the answer takes, citation format, or how it differs from 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?

Schema description coverage is 0%, so the description should compensate for the undocumented parameters, but it does not mention 'domain' or 'question' at all. The parameter names are somewhat self-explanatory, but no additional meaning or expected format/value constraints are added.

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 the resource ('a company') and output type ('grounded, cited answer'), but it is a noun phrase rather than a specific verb. It does not explicitly distinguish this from sibling tools like get_company or get_profile, which also concern company information.

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 about when to choose research_company over siblings such as get_company or compare_companies. The phrase 'grounded, cited answer' implies a research-oriented use, but there is no explicit when/when-not or alternative routing.

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 full behavioral disclosure. It transparently explains the discover:true side effect (searches the web, audits new products into the registry, slower and costlier), the filtering behavior, and the return of ranked products with reasons. It does not mention rate limits or auth, but for a tool of this nature these aren't critical.

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 dense paragraph, front-loaded with the core purpose. Every sentence adds value: the main behavior, the optional filters, and the discover side effect with cost implications. No fluff, though it could be split into bullets for readability—still appropriately sized.

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 7 params, no output schema, and a non-trivial discover behavior, the description provides enough to call it correctly: the task input, filter semantics, and the discover trade-off. It doesn't detail the exact output structure, but the description's statement about ranked products with reasons suffices for agent 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 explain parameters. It does: 'task' is the natural-language task, optional boolean flags (api/mcp/self_serve/openapi/cli) filter candidates, and 'discover' triggers web search and audit. All 7 params are effectively covered, despite the schema providing no descriptions itself.

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: it takes a natural-language task and returns products (ranked by fit and AgentReady score) that expose required capabilities, each with a reason. This is specific and distinguishes it from siblings like 'search_tools' or 'find_tools_for_task' by highlighting the resolution and ranking behavior.

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 sets clear context—it's for natural-language tasks—and explains optional filtering by capability type and the discover flag for broader web search. It doesn't explicitly name alternatives or state when not to use it, but the context is sufficient for an agent to infer applicability.

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 burden of behavioral disclosure. It states the tool searches the registry but does not explain return format, pagination, ordering, or any side effects. This is insufficient for an agent to understand what to expect from the call.

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, efficient sentence that packs the core purpose and key dimensions without fluff. Every word earns its place, and it is front-loaded with the primary action.

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 6 parameters, no output schema, and no annotations, the description is severely inadequate. It does not mention what results look like, how many results are returned, any filtering constraints, or how the boolean requirements interact with the query. An agent would have to guess critical details.

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 mentions 'requirements (api/mcp/self_serve/openapi/cli)' but does not explain what each boolean means or how they affect the search. This adds minimal value over the raw schema and fails to clarify parameter 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 clearly states the action ('Search') and resource ('the registry'), and specifies search dimensions (query + requirements). However, it does not explicitly differentiate from sibling tools like find_tools_for_task, which may also involve searching, so it loses a point for lack of sibling distinction.

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 provided on when to use this tool versus alternatives such as list_registry or find_tools_for_task. The description implies a search use case but gives no context or exclusions, leaving the agent to infer appropriateness.

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