AgentCrush

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

Annotations already define read-only, open-world, and idempotent behavior. The description adds meaningful context: it returns full per-agent scoring data plus comparison context, and notably reveals that the tool does not declare a universal winner — showing evidence differences. This goes beyond the annotations and helps the agent interpret results.

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 compact and well-structured: purpose, return value, usage, and a critical behavioral caveat are each covered in a single short paragraph. No filler or redundant phrases; 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 presence of an output schema and strong annotations, the description sufficiently covers the tool's function, return type, and usage. It could mention limitations or edge cases, but for a read-only comparison tool with sibling differentiation, it is quite 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 input schema already documents 'handles' as 'Array of 2-5 agent handles to compare' (100% coverage). The description merely restates '2-5 AI agents' without adding new parameter-specific detail. Baseline 3 applies because the schema carries the semantic load.

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 ('Compare') and resource ('AI agents'), and clarifies the scope ('across all their categories'). It also distinguishes from sibling tools like get_agent_details by framing it as side-by-side comparison, making the purpose unmistakable.

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 'Use for "X vs Y" queries', giving a clear when-to-use context. It also notes that no universal winner is declared, setting expectations for the output. However, it doesn't name alternative sibling tools or explicitly state when not to use it, so it stops short of a 5.

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?

Even with annotations declaring readOnlyHint, openWorldHint, and idempotentHint, the description adds substantial behavioral context: the 30-day Ghost Index liveness rule, trust tiers, verified payment rails (x402/MCP/ERC-8004), top-3 ranking, total match count, and the paid endpoint for the full list. This goes well beyond the annotations and gives the agent a clear model of behavior.

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: the first states purpose and return contents, the second gives the full-list URL and pricing. Every sentence earns its place, and the structure front-loads the most important 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?

Given the rich annotations, 100% schema coverage, and an output schema, the description is complete: it covers ranking criteria, safety indicators, filterable dimensions, output scope, and a follow-up endpoint. No critical usage context is missing for a read-only discovery 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 description coverage for all 5 parameters is 100%, so the baseline is 3. The description repeats some concepts (liveness, rails) but does not add new parameter-level meaning beyond the schema's own property descriptions. It neither hurts nor enhances parameter understanding materially.

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 opens with a clear, specific purpose: "Counterparty discovery: 'which agents can do X and are safe to pay?'" and details exactly what is returned (top 3 ranked candidates, liveness, trust tier, payment rails, scores, endpoints). This distinguishes it from sibling tools like search_agents by emphasizing safe-to-pay ranking and verified rails.

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 establishes clear context for when to use this tool (counterparty discovery for payable agents) and includes practical details like the full list link and cost. However, it does not explicitly state when not to use it or name alternatives (e.g., compare_agents, verify_counterparty), so it stops short of full exclusion guidance.

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

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

Annotations already mark the tool as read-only and idempotent, and the description aligns by stating it is a 'Mirror of GET /api/agent/{handle}/changes'. It adds behavioral nuance—it performs a 'pairwise delta scan' and reports only 'material changes', which clarifies the nature of output beyond the annotation flags. No contradictions.

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 three short, information-dense sentences. Each sentence contributes: defines the scan method, lists reported fields, and gives an API mirror. No filler.

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 a complete input schema, annotations, and an output schema present, the description covers the operation's essence and output characteristics sufficiently. It doesn't explain return structure (covered by output schema) and lacks explicit sibling comparison, but overall is complete for the tool's complexity.

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?

Input schema has 100% description coverage for all three params (handle, limit, since), so the schema already documents parameters. The description mentions 'recent snapshots' which relates to 'since' but adds no new parameter-level detail. Baseline 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 specifies a 'pairwise delta scan over an agent's recent snapshots' and lists concrete fields (score, rank, github_stars, etc.), making it distinct from siblings like compare_agents or get_top_movers. The verb 'scan' and resource 'agent's recent snapshots' are specific.

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 the tool's function but does not explicitly state when to use it instead of alternatives like get_agent_history or compare_agents. The 'per-agent' and 'delta scan' wording implies usage for change tracking, but no exclusions are given. This is adequate but lacks explicit 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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds valuable behavioral context beyond these: it discloses the fuzzy-match suggestion behavior on miss, and it describes the nature of the returned data (identity, raw signals, sub-scores, evidence-ready status). This is exactly the kind of context that helps an agent anticipate results. No contradiction.

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 three concise sentences. It front-loads the purpose, then details the return contents, then gives crucial miss-handling guidance. Every sentence earns its place and there is no fluff or redundancy.

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 purpose, the specific category scores, the return components, and the edge-case behavior when the handle is not found. The output schema exists and likely documents exact field structures, so the description need not repeat return format details. For a single-parameter read-only tool, this is complete and actionable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With a single parameter and 100% schema description coverage, the schema already thoroughly documents the 'handle' including format and examples. The description adds no additional parameter semantics beyond what the schema provides, so the baseline 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 uses a specific verb ('Get') and resource ('full details for a specific AI agent'), enumerates the included category scores (model_family, tokenized, service, developer), and lists specific return components (identity, raw signals, sub-scores, evidence-ready status). This clearly distinguishes it from sibling tools like get_agent_trust or get_agent_changes, which target narrower aspects.

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 clear context: use this tool to retrieve comprehensive agent details. It also provides an explicit behavioral instruction for not-found handles: 'LLMs should use these instead of hallucinating "agent doesn't exist"'. However, it does not explicitly name alternative sibling tools or state when to prefer one over another, so it misses the top tier for 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?

Annotations already declare readOnlyHint and idempotentHint, so the description adds value by disclosing behavior like daily snapshots and deduplication per calendar day, and the trend summary format. This goes beyond what annotations provide and does not contradict them.

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

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

The description is four concise sentences, each adding distinct value: purpose, data structure, output summary, and a use case. It is front-loaded with the main purpose and contains no redundant or vague language.

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 an output schema present, the description sufficiently covers what the tool does and returns (daily snapshots, trend summary) and the intended use case. It could mention edge cases or ordering, but the combination of schema, annotations, and description is largely complete for selecting this 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?

The input schema provides 100% coverage with descriptions for both 'days' and 'handle'. The description only reiterates the time range from the schema (1–90 days) and adds no new parameter semantics, so the baseline 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 states a specific verb ('Get') and resource ('rank and score history') with a clear time scope ('past 1–90 days'), distinguishing it from siblings like get_agent_details or get_agent_changes. It also specifies the output includes daily snapshots and a trend summary, which is unique to this tool.

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 a clear use case ('Useful for showing how an agent's standing has evolved'), giving context for when to use the tool. However, it does not explicitly name alternatives or state exclusions, so it falls short of the highest level.

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 cover read-only/idempotent safety, and the description adds meaningful behavioral context by listing the inputs to the score and noting the endpoint mirror. No contradictions with annotations.

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

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

Two sentences, front-loaded with the core purpose and output, then the composition detail. No wasted 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?

Given the tool's simplicity, rich annotations, and presence of an output schema, the description sufficiently covers function and composition. It lacks only explicit usage alternatives, which are not critical for this straightforward read-only 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 covers 100% of the single parameter (handle) with a clear description. The text adds no extra parameter guidance beyond that, so it meets the baseline for high schema coverage.

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?

Description clearly states the tool returns a composite trust score (0-100) with classification, and specifically names the constituent data sources (confidence_tier, evidence tier, ERC-8004, risk flags). This distinguishes it from sibling tools like get_agent_details or verify_counterparty.

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?

Provides context ('for delegation decisions') and implies a single-call alternative to multiple lookups, but does not explicitly name alternative tools or state when not to use it. No exclusions are given, making it usable but not strongly differentiated.

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, idempotentHint, and non-destructive behavior. The description adds useful behavioral context: results are ordered by composite score, all sub-scores are visible, and the default is evidence-ranked only. This goes beyond annotations without contradicting them, offering valuable insight into how the tool behaves.

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

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

The description is two short sentences, front-loaded with the primary function and a key detail about the output. It is concise, clear, and contains no filler or redundant repetition of schema data.

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 a clear output schema and robust annotations, so the description does not need to explain return values or safety. The description adequately covers purpose, ordering, and default filtering. The missing usage guidelines are a small gap, but for a simple ranking tool the description is otherwise 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 input schema has 100% description coverage for all three parameters, including enums and defaults. The description adds a little extra meaning by mentioning composite score and sub-scores, but most of the parameter semantics are already captured in the schema. The default evidence-ranked behavior is also present in the schema's default value, so the description does not add significant new information.

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 specifies the action ('Get'), the resource ('full ranking for one of the 5 categories'), and the output characteristics ('ordered by composite score with all sub-scores visible'). It distinguishes itself from sibling tools like compare_agents and find_agents by focusing on category-based ranking. However, there is a minor inconsistency: the description says '5 categories' while the schema parameter mentions '4 AgentCrush categories', which could confuse clarity slightly.

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 explicit guidance is given on when to use this tool versus alternatives. The description does not mention situations where another tool would be preferable, nor does it reference sibling tools or provide any exclusion criteria. This is a clear gap for an agent deciding between ranking, 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?

Annotations already declare read-only, idempotent, non-destructive. The description adds valuable context beyond annotations: it enumerates the exact data facets (counts, category mix, evidence-ranked, archived, 30-day snapshot volume) and notes it's an API mirror, which helps set expectations about output shape. No contradictions.

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, well-structured sentence with a clear lead ('One-call') followed by a colon-separated list of contents. Every element is informative and no filler exists. Highly 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 simplicity (no params), the description fully covers what the tool provides. An output schema exists, so return values are specified elsewhere. Sibling context and the list of contents make the tool's role clear and 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 tool has zero parameters, so the baseline is 4. The description does not need to explain parameter behavior because there are none. The schema is empty and fully covered, and the description adds all necessary context.

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

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

Description specifies a unique verb-resource pair: 'One-call ecosystem-level summary' with explicit contents (counts, category mix, leaders, snapshot volume). It distinguishes itself from sibling tools like get_category_ranking by covering the entire ecosystem rather than a specific category. The API mirror reference adds concrete grounding.

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?

Clear context provided: 'ecosystem-level summary' tells the agent when to use it (when needing a broad overview) versus more specific sibling tools. However, it doesn't explicitly name alternatives or state when not to use it, falling short of a 5.

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 and idempotentHint, so safety is covered. The description adds valuable context: 'Methodology travels with data' and the specific contents returned. This goes beyond what annotations convey and clarifies the tool's role.

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: the first states purpose and contents, the second gives a bolded usage guideline. It is efficient, front-loaded, and contains no redundant or filler words.

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 one parameter, full schema coverage, an output schema, and strong annotations, the description covers all necessary context: what the tool returns and when to invoke it. Nothing critical is missing for a low-complexity read-only retrieval 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 is 100% and the single parameter 'category' has an enum with descriptions. The description adds only the phrase 'one category' and does not elaborate on parameter choices or formats, so it provides no additional value over 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 retrieves 'the scoring methodology for one category' and enumerates its contents (weights, signal sources, formulas, evidence-ready rule, known limitations). This goes beyond a simple restatement and strongly distinguishes it from sibling tools like get_category_ranking.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says to call this tool 'when explaining HOW a ranking works' and frames the benefit as 'methodology-accurate answer instead of guessing'. This gives clear usage context, though it does not name alternative tools or state when not to use it.

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

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

Annotations already declare the operation as read-only, idempotent, and non-destructive. The description adds meaningful context by defining what is counted ('indexed agents') and enumerating the protocol/surface categories, which clarifies the tool's behavior without contradicting 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?

A single sentence delivers the full purpose, scope, and example categories with no filler. The structure is ideal for quick comprehension by an agent.

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 parameters, a rich annotation set, and presence of an output schema, the description fully covers the tool's context. It explains what the tool counts, which protocols/surfaces are covered, and when it is useful, leaving no critical gap.

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 no parameter explanation is needed. Per the rubric, baseline for zero params is 4, and the description correctly focuses on the tool's purpose rather than nonexistent 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 clearly states the tool provides counts of indexed agents per major protocol/surface, listing specific examples (ERC-8004, Virtuals, Agentverse, x402/Bazaar, HuggingFace, GitHub). This specific scope differentiates it from sibling tools like get_ecosystem_summary or get_category_ranking.

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 notes it is 'useful for ecosystem-state questions,' providing clear usage context. However, it does not name alternative tools or specify when not to use this tool, so it lacks explicit exclusions.

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. The description adds useful context by specifying the computation source (agents.weekly_delta) and the default limit of 10 per direction, which goes beyond the annotation metadata without contradicting it.

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 concise sentences, front-loaded with 'Returns' and no filler. It efficiently communicates the core functionality and the default behavior.

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 all parameters optional and well-documented, an output schema present, and annotations covering safety, the description provides sufficient context for a read-only query tool. It clearly answers what, when, and basic behavior without needing to explain return values thanks to the 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 description coverage is 100% for all three parameters, each with its own description and defaults. The description does not add parameter-specific information beyond the schema, 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 the tool returns top weekly rank movers computed from agents.weekly_delta, with up and down directions. It uses a specific verb ('Returns') and resource ('top weekly rank movers'), which makes it distinguishable, although it does not explicitly name sibling alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'Useful for surfacing notable changes since last week' provides clear context on when to use the tool. It does not enumerate when not to use it or mention alternative tools, so it misses the top tier, but the context is still informative.

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

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the tool is known to be safe. The description adds context beyond the annotations by specifying the output includes 'tracked + evidence-ranked counts and current methodology versions,' which gives insight into the data's nature. It does not contradict the annotations and provides useful behavioral context without overexplaining.

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, with the first sentence front-loading the core action and the second providing a clear use case. Every sentence contributes value: one states what the tool does, the other states when to use it. There is no redundancy or filler.

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

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

For a simple list tool with no parameters, rich annotations, and an output schema, the description is complete. It covers what the tool returns (categories, counts, versions) and when to use it. The output schema handles return value details, so nothing more is needed.

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 parameter semantics are trivially fully covered by the empty schema. The description doesn't need to explain any params, and baseline for 0 parameters is 4. The description doesn't add anything about parameters, but that's expected and appropriate here.

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: 'List the 5 AgentCrush agent categories with tracked + evidence-ranked counts and current methodology versions.' It uses a specific verb ('List') and a specific resource ('AgentCrush categories') with additional scope (5 categories, counts, versions). This distinguishes it from sibling tools like get_category_ranking or get_ecosystem_summary, both of which serve different purposes.

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 usage context: 'Use this for market-level discovery — what kinds of agents does AgentCrush track and how many of each?' This tells the agent when to use the tool, but it doesn't explicitly mention alternatives or when not to use it. Given the simplicity of the tool, this is sufficient, but it lacks the explicit exclusion or alternative naming required for a 5.

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 cover read-only and non-destructive behavior, and the description adds value by disclosing the evidence-ranked nature of the index and the forward-compatibility promise for filters. This goes beyond the minimal annotation coverage, though it does not discuss rate limits or pagination behavior.

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: the first states the core purpose and return value, the second explains filter usage and future compatibility. It is front-loaded and every sentence earns its place with no redundant filler.

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 a nested filters object and an output schema, which cover parameter details and return shape. The description adds domain context (evidence-ranked index) and API stability note, making it reasonably complete. It lacks guidance on choosing between sibling search tools, but the schema and annotations cover most operational aspects.

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 all parameters are documented. The description adds only that filters are 'structured constraints' and mentions future filter keys, which is not immediate semantic detail beyond the schema. Baseline 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 a specific verb ('Search') and resource ('AI agents across AgentCrush's evidence-ranked index'), and notes the return info (category, tier, rank). However, it does not differentiate from the sibling tool 'find_agents', which likely has a similar purpose, so it misses the sibling distinction needed for a 5.

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 usage for name/keyword search and mentions using the 'filters' object for structured constraints, but it does not specify when to choose this over alternatives like 'find_agents' or 'compare_agents'. No exclusions or explicit 'use this when' guidance 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?

Beyond the annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint), the description discloses a specific behavioral rule: 'Liveness-aware: an agent with no public activity signal in 30+ days never gets a clean proceed, even if well-ranked.' It also mentions that the call is free and that pointers to paid analysis are included. This adds valuable behavioral context not present in 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 concise, front-loaded, and impactful. The first sentence immediately communicates the tool's value proposition, followed by a specific behavioral note and usage guidance. Every sentence earns its place, with no redundant or vague wording.

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 (one parameter) and the existence of an output schema, the description is complete. It covers the outcome (proceed/caution/reject with reasoning), the liveness behavior, usage context, and even mentions pointers to paid deeper analysis. No essential context is missing.

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 100% coverage of the single 'handle' parameter with a clear description ('Counterparty agent handle slug (e.g. "crewai")'). The tool description does not add new parameter details beyond the schema, but it does provide context for how the handle is used in the pre-transaction decision. Per the rubric, a baseline of 3 is appropriate given high schema coverage.

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-resource pairing: 'should my agent deal with this counterparty right now?' It returns 'proceed / caution / reject with reasoning,' which distinguishes it from sibling tools like compare_agents or get_agent_trust. The phrasing 'THE pre-transaction question' firmly establishes its unique role.

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?

Explicit usage guidance is provided: 'Use before paying, delegating to, or integrating any agent.' It also mentions alternatives by noting that deeper analysis (full risk decomposition, history, signed attestation) is paid, with pointers included in the response. This gives clear when-to-use and when-to-consider-other-tools context.

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