Sato Hub: Onchain Agents

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

Beyond annotations (readOnlyHint, idempotentHint, etc.), it clarifies 'Read-only' and specifies error conditions for unknown slugs, adding practical behavioral context.

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 plus an example, front-loading the core purpose and listing return fields without unnecessary 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?

Despite no output schema, it comprehensively lists return fields (identity, agent types, chains, etc.) and error handling, making it 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?

Schema coverage is 100% and description repeats schema details. It adds value by referencing search_agents for the slug, but does not significantly extend meaning 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 explicitly states 'Get the full Sato Agent Passport manifest' and lists its contents, clearly distinguishing it from sibling tools like onchain_agent_get_deploy_spec or onchain_agent_get_metrics.

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 advises using onchain_agent_search_agents to find slugs and provides an example. It does not explicitly exclude other tools but the context is clear for passport retrieval.

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 adds significant behavioral context beyond annotations: it explains deploy_status as a trust signal, warns about verification, notes error cases, and explicitly states read-only. This is rich and honest.

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 thorough but well-structured, front-loaded with the main purpose, and includes an example. Each sentence adds value, though it could be slightly more compact without losing detail.

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?

Despite no output schema, the description fully documents return fields, error cases, and caveats. It provides all necessary 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%, so baseline is 3. The description adds meaning for slug (e.g., example usage) but does not elaborate on response_format beyond what the schema provides. No degradation or improvement from baseline.

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 it gets the deploy manifest for a resource by slug, specifically calling out the essential install-and-instantiate information. This distinguishes it from sibling tools like get_resource or get_agent_passport.

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 obtaining deploy specs to build from a resource, but does not explicitly contrast with siblings or provide when-not-to-use scenarios. The error case is mentioned, but alternative tools are not discussed.

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. The description adds value by specifying data sources (Ethereum mainnet) and clarifying what is not included ('never the whole agent-token category'). It also lists the return shape. 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 concise paragraphs: the first describes the tool's purpose and data scope, the second lists the return JSON structure. No unnecessary words; front-loaded with key information. Every sentence is 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?

Despite lacking an output schema, the description provides a detailed breakdown of the return JSON fields. Both parameters are well-documented in the schema. The tool is simple (read-only, two optional params), so the description is adequate. Minor gap: no mention of error conditions or rate limits, but not crucial for a read-only metric 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% with detailed descriptions for both parameters (token_limit and response_format). The description provides no additional parameter meaning beyond what the schema already conveys, so baseline score of 3 applies.

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 it retrieves live ecosystem metrics: ERC-8004 registered-agent count and curated Top Project Tokens index. It uses specific verbs ('Get live ecosystem metrics') and resources (ERC-8004, Top Project Tokens), distinguishing itself from sibling tools like onchain_agent_get_agent_passport or onchain_agent_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?

The description implies the tool is for fetching metrics, with no explicit guidance on when to use it vs. alternatives. It does not state when not to use it or mention alternative tools for different metric needs. The annotations confirm read-only, idempotent behavior, but no usage context beyond that.

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 readOnly=true, idempotent=true, and destructiveHint=false. The description adds 'Read-only' and details the return structure and filtering behavior, which is consistent with annotations and provides extra context.

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, well-structured: purpose, filtering options, return format, and example. Every sentence adds value, and it is 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?

The description covers the tool's purpose, sources, filtering, pagination, and return format. It lacks error handling or edge cases, but for a read-only tool with good annotations, it is fairly 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?

Schema coverage is 100% with clear parameter descriptions. The description summarizes filtering and pagination but does not add significant new info beyond what is in the schema. The example is helpful but does not increase parameter 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 it 'Get[s] the Onchain Agent news feed' with specific sources (GitHub, X posts, RSS). It distinguishes from sibling tools by being the only news-related tool, and includes an example.

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 filtering by kind and chain, pagination, and provides an example. It does not explicitly mention when not to use, but as the sole news tool, context is clear.

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 provide readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=true. The description adds that it's read-only, describes return structure (resource + recent_activity), error conditions, and includes an example. 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?

Two concise sentences plus a note on return and example. Front-loaded purpose, no wasted 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?

Given no output schema, the description explains the return format (JSON with 'resource' and 'recent_activity') and error conditions. It omits clarification that response_format parameter controls output type, but overall covers the main use cases.

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 descriptions. The description adds minimal extra meaning: it mentions 'by slug' and 'optionally with its recent activity feed', and shows an example. Baseline 3 is appropriate as it does not significantly enhance parameter 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 verb 'Get' and the resource 'full record for one directory resource by slug', differentiating it from search tools like onchain_agent_search_resources. It also specifies optional inclusion of recent activity feed.

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 advises using onchain_agent_search_resources first to find a slug, and mentions error conditions (unknown slug or Deprecated resource). No explicit when-not-to-use or alternatives beyond the one sibling.

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

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

Annotations already indicate read-only, idempotent, open-world, and non-destructive behavior. The description adds that the tool returns a JSON object, errors on unknown slugs, and explicitly states 'Read-only'. This complements the annotations well without 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?

Extremely concise: two sentences plus an example. No filler words. The most critical information is front-loaded, and the example is directly helpful.

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 get-by-slug tool, the description covers all necessary aspects: what the page contains, how to obtain the slug, error handling, output format options, and the read-only nature. No gaps are apparent.

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 purpose of the 'slug' parameter (to identify the page) and references the list tool. It also provides an example and mentions the 'response_format' parameter's default and output types, 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 verb 'get', the resource 'wiki page', and the method 'by slug'. It also differentiates from sibling tools by mentioning `onchain_agent_list_wiki_pages` for finding slugs.

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 clear context on when to use the tool (to fetch a full wiki page by slug) and directs the agent to the list tool for slug discovery. It also notes that an error is returned for unknown slugs. However, it does not explicitly state when not to use it beyond that.

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 provide readOnlyHint, openWorldHint, idempotentHint, destructiveHint. Description adds return structure '{ total, categories: [{ name, count }] }' and states 'Read-only', reinforcing annotations. Moderate added value.

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: first states purpose with sorting behavior, second gives usage context and return format. Front-loaded and efficient, no wasted 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?

For a simple list tool with one optional parameter, clear annotations, and no output schema, the description covers purpose, usage, return format, and safety. Siblings provide context for filtering.

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 fully described. Description does not add details to the parameter, so 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?

Description clearly states 'List all resource categories with counts, most populated first.' Verb 'list' and resource 'resource categories' are specific. Among siblings, it differentiates from search_resources by providing categories for filtering.

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 'Useful before filtering onchain_agent_search_resources by category', providing clear context and alternative. Does not explicitly state when not to use, but the guidance is strong.

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

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

Annotations already indicate read-only and non-destructive. Description adds return format (JSON with total and chains array) and ordering behavior (spotlight first), adding context beyond 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?

Extremely concise: two sentences covering purpose, output format, and read-only nature with zero wasted 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?

Adequate for a simple list tool with one optional parameter. Provides return structure example but lacks details on pagination or invariant ordering.

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 full documentation for the single parameter response_format. Description adds no additional meaning 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?

Description clearly states the tool lists all blockchains in the directory with resource counts and spotlight ordering. It distinguishes from sibling tools that handle agents, resources, categories, etc.

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?

Implied usage when chain information is needed, but no explicit guidance on when to use this vs other list tools like list_categories or list_wiki_pages.

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 provide readOnlyHint, idempotentHint, destructiveHint. Description adds return structure (JSON with total and pages) and reiterates read-only. With good annotation coverage, description adds modest context.

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 concise sentences, front-loaded with core purpose. No unnecessary words. Efficiently conveys key info.

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?

Provides return format, fields, and read-only nature. Lacks details on pagination or ordering, but given simplicity of tool, it is largely 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?

Schema covers the only parameter (response_format) with enum and default. Description adds minimal value beyond schema, specifying output format descriptions. Baseline 3 due to 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 'List all Onchain Agent wiki pages' specifying exact fields (slug, title, keyword, summary, last_updated) and return format. Distinguishes from sibling tools like get_wiki_page (single page) and search_agents (different resource).

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?

Implied usage by stating 'List all', but no explicit when-to-use or when-not-to-use. Alternatives are not mentioned. However, sibling tool names provide some 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?

Beyond annotations (readOnly, idempotent, non-destructive), the description adds transparency by specifying the data source (daily snapshots + change-event log) and that high-signal only events are returned (passive drift suppressed). This gives the agent a better understanding of what to expect.

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 and front-loaded with the purpose. It covers purpose, usage, event types, data derivation, return format, and example in a compact manner without unnecessary words. A small improvement would be better structuring of the return format explanation.

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?

Despite no output schema, the description fully explains the return format (JSON structure with scope, total, and changes array) and includes tone attribute. It also covers event types and derivation, making the tool's behavior complete for 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 100% with detailed parameter descriptions. The description provides an example usage ({ days: 7 }, { slug: 'coinbase-agentkit' }) but does not add substantial new meaning beyond the schema. Given high coverage, a 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 retrieves recorded changes across the directory, i.e., the auditable listing history. It distinguishes between site-wide feed and single resource history, and lists specific event types, making it distinct from sibling tools that focus on individual data points.

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 omit or include the 'slug' parameter for site-wide vs. resource-specific history. It does not explicitly discuss when not to use this tool or mention alternatives, but the context is sufficient for an agent to decide.

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

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

Annotations already indicate read-only, open-world, idempotent, non-destructive. The description adds transparency about ranking criteria (openness/activity/verifiability), explicitly states no safety/quality/returns judgment, and mentions the handling of gaps. 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 concise, with two clear sentences plus an illustrative example. Every word adds value, and the structure is easy to parse.

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

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

Without an output schema, the description sufficiently explains the output structure (slots, scores, gaps) and ranking criteria. All four parameters are documented in the schema, and the description covers what the agent needs to know to use the tool effectively.

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 coverage is 100%, so each parameter is already described. The description provides an example usage but does not add new semantic details beyond the schema, achieving the baseline for well-documented parameters.

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

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

The description states exactly what the tool does: given a goal, it returns a trust-ranked stack of directory resources bucketed into specific slots. It distinguishes itself from sibling tools like search or get resource by focusing on stack recommendation with rankings and gaps.

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 clearly indicates when to use (given a goal) and provides an example input. It does not explicitly state when not to use or mention alternatives, but the usage context is clear from the description and sibling list.

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 adds significant context beyond annotations: it explains that only human-review-listed agents are returned, the trust rule regarding verification_status, and the return format. Annotations already declare read-only and idempotent, so 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 concise and well-structured: it front-loads the main purpose, then adds trust and return details, and ends with an example. Every sentence adds value without 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?

With no output schema, the description fully specifies the return structure, includes trust guidance, and covers all parameters (via schema). This is complete 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%, so baseline is 3. The description adds value by summarizing filter capabilities and providing an example, helping agents understand how to combine parameters effectively.

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 searches registered onchain agents in the Sato Agent Registry, distinguishing it from the resource directory and sibling tools. It uses a specific verb ('search') and resource ('registered onchain agents'), making its 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 provides filtering options and explicitly contrasts with the resource directory, guiding when to use this tool. However, it could more explicitly state when not to use it or alternative tools, but the context is sufficient for most 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?

Annotations already mark the tool as read-only, open-world, and idempotent. The description adds that deprecated resources are never returned and clarifies the output format and pagination behavior, supplementing the annotations without 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 well-organized with sections for filters, examples, and return format. It is somewhat lengthy but each part is useful. A slight reduction could improve conciseness, but it is not bloated.

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 18 parameters with full schema coverage, no output schema, and good annotations, the description provides complete context: it lists all filter options, explains pagination, states the response structure, and gives practical examples. No gaps are evident.

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 descriptions already present. The description adds value by explaining AND-matching for the query parameter, listing legacy flags, providing examples mapping user intent to parameter values, and grouping related filters. This exceeds the baseline of 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 states it searches the Onchain Agent directory of agents, frameworks, skills, and tooling, which is a specific verb and resource. It differentiates from siblings like onchain_agent_get_resource (single resource retrieval) and onchain_agent_search_agents (likely narrower search), making its scope 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?

The description provides explicit usage context through example queries and filter explanations, but does not explicitly state when not to use this tool or compare it directly to alternatives. However, the examples and filter list cover common use cases.

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