agentery

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

No annotations provided, so description carries full burden. Discloses all return fields: observed price, upvotes, sector, how_to_connect object, reported_success with explanation of null condition (5 distinct reporters in 90 days).

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?

Four sentences, each with distinct purpose: usage, output contents, additional field semantics, and next step. No redundant or extraneous text.

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?

No output schema, but description fully covers return object including fields and special semantics. Also suggests follow-up action (report_outcome). Complete for a comparison tool.

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 100% but description adds value by specifying source (from search_agents/market_gaps), bound on count (2-6), and example format. Clears ambiguities in parameter usage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States 'decide between shortlisted agents' with specific output including evidence-scored cards, price, upvotes, and sector. Distinguishes from search_agents and get_agent by focusing on comparison of multiple handles.

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?

Explicitly says 'call this to decide between shortlisted agents' and references source from search_agents/market_gaps. Mentions follow-up action (report_outcome) but does not explicitly list when not to use or compare to all siblings.

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 bears full burden. It explains the tool returns aggregated, ranked miss counts, implying a read-only query. It doesn't mention authorization or side effects, but the behavior is clear enough for a simple read operation.

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 sentences, front-loaded with the core purpose. The second sentence adds audience and pairing advice. No wasted words; every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (1 param, no output schema), the description is sufficiently complete: it defines the signal, its use case, and how to combine it with siblings. A note on pagination or default limit would be a minor improvement.

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 100% with one parameter (limit) fully documented. The description does not add new parameter-specific details beyond what the schema says, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states this tool surfaces 'capability queries that returned ZERO results' – a specific unmet-demand signal. It distinguishes from siblings like search_agents (existing agents) and market_gaps (sizing), making the purpose 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?

The description explicitly says when to use it: to see searches for non-existent agents. It recommends pairing with niche_report/market_gaps. It doesn't explicitly list when not to use it, but the context and sibling names imply differentiation.

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 provided, but description details the returned fields and conditions (e.g., when structured profile available). No mention of side effects or errors, but adequate for a read tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence front-loaded with core purpose, no wasted words. Clearly 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?

Lists typical response fields, but lacks details on error handling, priority if both parameters given, or pagination. Adequate given no output schema.

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 100% with clear descriptions. Description adds little beyond mentioning handle and registration number, but does reinforce the two ways to call the 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?

Clearly states the tool retrieves the public directory card for one agent by handle or registration number, listing specific fields. Distinguishes from sibling tools like search_agents.

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?

Explicitly states when to use (for a single agent's card). While no explicit alternatives or exclusions, the context implies use for single retrieval versus search or comparison tools.

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 burden. It details the return object (evidence-scored profile, how_to_connect, reported_success), including when fields are null. Adding an explicit 'read-only' statement would further improve 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?

Description is long but every sentence adds value. It front-loads the main purpose and then lists details in a structured way. Could be slightly more concise but well organized.

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, the description thoroughly explains the return structure (fields, nulls, reported_success condition). Complete enough for an AI agent to understand the tool's output.

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 100%, baseline is 3. Description adds value by noting the agent_id comes from search_agents or compare_agents, providing context beyond the 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's purpose: to drill into one agent's detailed profile after using search_agents or compare_agents. It lists the included fields, distinguishing it from sibling tools like search_agents which return lists.

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?

Explicitly says when to use it ('after search_agents or compare_agents') and provides follow-up guidance ('If you use the listing, call report_outcome afterwards'). This establishes clear context and alternatives.

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

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

No annotations provided, but the description details the tool's behavior: it excludes crowded niches by default, provides gap_score, plain-English why, and market pulse. It is transparent about what the tool returns and its ranking logic.

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 front-loaded with the main purpose and provides essential details without excessive verbosity. It could be slightly more concise but remains efficient.

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 complexity and lack of output schema, the description provides a thorough explanation of what each result includes (gap_score, why, crowding, etc.). It enables effective use without ambiguity.

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 100%, so baseline is 3. The description adds value by explaining the default rank value, the meaning of 'hot' versus 'gaps', and the optional sector filter, going beyond the schema 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 tool finds under-served markets, with specific verb and resource. It distinguishes itself from sibling tools by focusing on market gaps and offering two ranking modes.

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 explains when to use default 'gaps' vs 'hot' ranking, and mentions drill-down with niche_report. It provides clear context but lacks explicit exclusion cases.

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 burden. It lists all returned fields (market_pulse, crowding, adjacent niches, etc.) and notes that 'movement' and 'index_series' can be null. No side effects are mentioned, but for a read-only report 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 dense paragraph but front-loads the purpose and key fields. It could benefit from structuring (e.g., bullet points), but is concise and informative.

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 1-parameter tool with no output schema and no annotations, the description adequately covers the purpose, input source, and output fields including nullability. It provides enough context for an agent to use the tool 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 coverage is 100% with one parameter 'niche'. The description adds value by instructing 'Get valid slugs from market_gaps' and provides an example 'ai-phishing-detection', supplementing the 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's purpose: 'deep-dive ONE market niche before building or investing'. It specifies the resource ('market niche') and the action ('deep-dive'), and distinguishes itself from sibling tools like 'market_gaps' by indicating it provides detailed data.

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 tells when to use the tool ('before building or investing') and how to get valid input slugs from 'market_gaps'. It does not explicitly exclude alternatives, but provides clear prerequisite and 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?

No annotations are provided, so the description carries full burden. It thoroughly discloses behavioral traits: returns pricing distributions per persona tier, billing mix, and free-tier share. It explains the index (chained, like-for-like, base date, null when short series) and when index_by_tier is null (with niche/sector filter). This exceeds typical 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 front-loaded with the main purpose and is dense with information. Every sentence adds value, covering scope, index mechanics, and null cases. While it is somewhat long, it avoids redundancy and earns its structure.

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?

With no output schema, the description successfully explains return values (pricing distribution, index, index_by_tier) and edge cases (null conditions). It covers scope behavior and parameter interactions. Missing error handling or rate limits, but given two optional parameters and a well-scoped tool, this is adequate.

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 100% (both parameters have descriptions). The tool description adds significant meaning beyond schema: it explains that niche overrides sector, and details behavior for each scope (whole economy vs filtered). This enhances parameter understanding, justifying a score above baseline 3.

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 learn pricing costs before choosing. It specifies the output (observed-pricing distribution, index, index_by_tier) and scope options (niche, sector, whole economy). This distinctively sets it apart from sibling tools like search_agents or compare_agents.

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 advises 'before choosing' as the context for use. It explains when to use which filter (niche, sector, or none) and details behavior for different scopes, such as index_by_tier being null with filters. However, it lacks explicit comparisons to sibling tools or 'when not to use' 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?

With no annotations, the description fully covers behavior: it reads real agent profiles, never invents capabilities, and returns 'unclear' for missing evidence. This transparency about data sourcing and honesty is valuable for an AI 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, one sentence covering access, core function, use case, and behavior. It is front-loaded with critical info (partner-only) and uses no filler. Minor improvement could be breaking into bullet points for scanability.

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 complexity (nested objects, 3 params, no output schema), the description explains the structured output (scored matches with reasons/cautions) and core behavioral traits. It could detail the output structure more, but it is adequate for 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?

The input schema covers all parameters (100% coverage). The description adds meaning by explaining that workflow_steps are per-step inputs and business_context provides context for ranking, enhancing understanding beyond the 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's purpose: given a business context and workflow steps, return ranked agent candidates for each step with match scores, reasons, and cautions. It distinguishes itself from siblings like search_agents and suggest_alternatives by focusing on per-step ranking for automation assembly.

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 says it's partner-only and intended for app builders assembling automations, providing clear context for when to use. It does not explicitly state when not to use or contrast with other tools, but the context implies it's for multi-step workflow scenarios.

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 fully discloses behavioral traits: reports are correlated with recent retrievals, unmatched reports are stored but unweighted, aggregation requires 5+ reporters, and rate limit doubling occurs after 5+ correlated reports. It also mentions the x-agentery-key header for identity tracking.

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 relatively long but front-loaded with the primary purpose and each sentence contributes meaningful information. It could be slightly more concise, but it is 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?

Given the tool's complexity, no output schema, and no annotations, the description is highly complete. It explains the reporting workflow, weighting, aggregation, rate limit effects, and header usage, leaving no critical 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 coverage is 100%, so the baseline is 3. The description adds no per-parameter details beyond the schema; it focuses on overall context. No additional parameter semantics 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 clearly states the tool's purpose: 'report whether it worked' after using a listed agent. It specifies the action (report outcome) and the resource (agent used), and distinguishes from sibling tools like search_agents and get_agent_profile by focusing on post-use feedback.

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 guidance on when to use the tool (after using a listed agent) and details conditions for weighted reports, aggregation, and rate limit benefits. It implicitly differentiates from siblings but does not explicitly state when not to use or compare 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It transparently explains the ranking mechanism (match_score), the inclusion of observed-price objects, filtering options, sorting, and the how_to_connect field. It also notes the requirement to call report_outcome after using results. While it doesn't explicitly state rate limits or permissions, it provides sufficient behavioral context for an AI 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 relatively long but every sentence adds value. It front-loads the key instruction ('START HERE') and follows with specific details about results, filtering, and follow-up. It is well-structured and informative, though slightly verbose. A more concise version could be written, but current length is justified by the amount of useful guidance.

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 7 parameters, no output schema, and no annotations, the description does a commendable job covering the tool's purpose, parameter semantics, and expected behavior. It explains the return fields (match_score, match_reasons, observed-price, how_to_connect) and post-invocation action (report_outcome). It lacks explicit output schema details, but the description provides enough context for an agent to understand what to expect. A brief mention of pagination or rate limits would improve completeness.

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 100%, so baseline is 3. The description adds significant value beyond the schema: it explains the 'START HERE' context, the importance of observed-price for shopping by value, the meaning of sort options (price_asc sorts cheapest first), and the purpose of how_to_connect. It also clarifies that max_monthly_usd drops agents above a threshold and that require_public_price filters further.

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: a filtered free-text search over the directory, ranked with match_score and match_reasons. It uses a strong verb ('search') and specifies the resource ('directory of agents'). It distinguishes itself from sibling tools like compare_agents and get_agent by being the starting point for finding agents.

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 says 'START HERE when you need an agent for a capability,' providing clear context for when to use this tool. It also mentions alternatives: get_agent_profile for full details and report_outcome for follow-up. This gives agents clear guidance on tool selection and post-invocation actions.

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 fully discloses the returned data (price, liveness, upvotes, how_to_connect) and the logic (same niche first, then similar capability, cheaper_only filtering). It does not mention error handling or empty results, but covers key behaviors.

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 sentence that conveys purpose, usage, and return info. It is concise but slightly long; front-loading the condition improves readability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (3 params, no output schema), the description covers purpose, when to use, key parameters, and return fields. It lacks details on pagination or errors but is sufficient for basic 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?

All parameters have schema descriptions (100% coverage), so baseline is 3. The description adds value by explaining the intent of cheaper_only ('shop down from the subject's price') and provides an example for agent_id ('openhands'), which aids understanding.

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 finds substitutes for a given agent, specifying the context (too expensive, unreachable, poor fit) and the order (same niche first, then similar capability). It distinguishes from sibling tools like search_agents and compare_agents.

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?

Explicitly states when to use: when a shortlisted agent is too expensive, unreachable, or a poor fit. It implies that for direct comparisons or general search other tools are appropriate, but does not explicitly exclude alternatives.

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