Dual Registry

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

The description offers a hint about a selection preference ('prefer listings...'), but does not disclose whether this is a read-only calculation, a mutation, or requires authentication. With no annotations provided, the description carries the full burden and fails to explain return values or side effects.

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

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

The description is extremely short (one fragment), but it is under-specified rather than concise. A single ambiguous sentence does not effectively communicate the tool's 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?

Given no annotations, no output schema, and two undocumented parameters, the description is wholly insufficient for an agent to determine what inputs are needed, what the tool returns, or how it behaves.

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

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

The schema provides no descriptions for 'listing_id' or 'listing_ids' (0% schema coverage), and the description does not mention parameters at all. An agent cannot infer the semantics of accepting either a single ID or an array, or what relationship they have to each other.

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 vague noun phrase ('Abundance ranking boosts') without a clear action verb or result. It mentions 'prefer listings that raise composition/outcome value for others,' but does not state whether the tool returns a ranking, modifies data, or scores listings. This is a vague purpose rather than a tautology.

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

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

There is no statement about when to use this tool versus alternatives like 'attract_buyers' or 'follow_trail.' No context, prerequisites, or exclusions are 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?

With no annotations, the description carries full burden, but it only includes a POST endpoint URL. It fails to disclose side effects, permissions, rate limits, or return behavior, which is a significant gap.

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

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

The description is a single sentence, but it is under-specified rather than concise. It omits essential guidance and uses unexplained terms like 'Active projections', making it unhelpful.

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 or annotations, this description is inadequate for a tool with three parameters. It lacks return value information, usage context, and any behavioral notes, leaving the agent to guess.

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

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

Schema description coverage is 0%, and the description adds no meaning to q, limit, or federation. The raw schema provides defaults and an enum, but the description does not explain what these parameters do or how they affect results.

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 'Agentic Resource Discovery over Dual catalog + Active projections' lacks a clear verb and resource. It is a noun phrase with jargon, leaving the operation ambiguous. It does not differentiate from sibling tools like search_active or hyper_index.

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

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

No guidance is provided on when to use this tool versus alternatives. The description contains no context about prerequisites, exclusions, or suitable 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 carries the full burden of behavioral disclosure. It mentions 'signed public' but does not explain side effects like irreversibility, permission requirements, or on-chain visibility. No details about what happens after issuance are provided.

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

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

The description is short and front-loaded with the action, but 'First principles:' is wasted words that do not help the agent. It is more under-specified than concise, lacking essential details for a tool with six parameters.

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 is complex with six parameters, an enum, and a nested object, yet the description does not explain the meaning of most parameters, the different attestation types, or the return value. With no output schema and low schema coverage, the description is far from 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 description coverage is only 17% (only subject is described), yet the description adds no meaning for body, claims, listing_id, or expires_hours. It repeats four of the enum values already present in the schema, adding no semantic value beyond the structured data.

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 the specific verb 'issue' and names the resource 'signed public attestation', clearly indicating the tool's purpose. It lists several attestation types, but does not explicitly distinguish from sibling tools like verify_attestation or bind_identity, though the action itself is distinct.

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

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

No guidance is provided on when to use this tool versus alternatives such as bind_identity or verify_attestation. The description only states what the tool does, not the appropriate context or 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?

The description discloses no behavioral traits. It does not say whether the tool reads data, computes values, or triggers side effects. It also fails to mention return types, rate limits, or any operational context. With no annotations to lean on, the description carries the full burden and provides essentially nothing about 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 very short, but it is under-specified rather than concise. It is a fragment of a sentence that obfuscates rather than clarifies. A concise description would be both short and information-dense; this one is short but lacks essential information, so it does not earn 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?

The tool has a single parameter, no output schema, and no annotations, making the description the sole source of context. The description is far from complete: it does not state the tool's purpose, behavior, or parameter meaning. Even for a simple tool, this is inadequate for an agent to decide when to invoke it or what to expect.

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 only parameter 'limit' is completely undocumented in the schema (0% coverage) and the description does not mention it at all. The description adds nothing to help the agent understand what the limit applies to or how it should be set. For a low-coverage parameter, the description was supposed to compensate, but it does not.

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

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

The description is a noun phrase that essentially restates the tool name: 'attractor-only growth targets' is just 'attractor targets' with extra words. It lacks a clear action verb, so it does not state whether the tool computes, retrieves, or ranks these targets. The formula 'hot trails × outcomes × liveness' hints at subject matter but does not clarify the operation. This is closer to a tautology than a clear purpose statement.

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 when-to-use or when-not-to-use guidance is provided. The phrase 'for outbound amplification' gives a slight contextual hint, but it is not sufficient to distinguish when this tool should be used over siblings like 'get_acceleration' or 's_curve_board'. No alternatives or exclusions are mentioned.

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 present, so the description must disclose behavioral effects. 'Bind' implies a mutation, but the description does not state side effects, authorization needs, reversibility, or what 'content-addressed capability' entails. This is too abstract to inform an agent about consequences.

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

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

The description is one sentence, but the 'First principles:' opener is filler and the sentence conveys little concrete information. It is short but not effectively structured or 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?

With 5 parameters, no output schema, no annotations, and no parameter guidance, this description is severely incomplete. An agent cannot determine input semantics, expected return values, or operational requirements.

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

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

Schema description coverage is 0%, and the description adds no parameter-level meaning. It mentions 'DID / public key' but does not clarify the roles of 'name', 'public_jwk', 'public_key_pem', or the required 'listing_id'. The agent is left to infer everything from property names.

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 identifies a specific action ('bind') and resources ('cryptographic identity (DID / public key) to listing + content-addressed capability'), which is distinct from sibling tools like attest or verify_attestation. However, the 'First principles' framing is vague and not operational.

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

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

No guidance is provided on when to use this tool versus alternatives such as attest, endorse, or verify_attestation. There is no mention of prerequisites, scenarios, or exclusion conditions.

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

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

No annotations are provided, so the description carries the full burden of disclosure. It does not state whether the tool mutates state, returns a value, or requires permissions. The phrase 'Optionally register' implies possible side effects but does not explain what registration entails or whether it is reversible.

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

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

The description is short but under-specified. The first clause ('First principles...') is philosophical and does not convey actionable information, while the second clause is too terse to add useful context. The structure sacrifices clarity for brevity.

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

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

Given 8 parameters, no annotations, and no output schema, the description is gravely incomplete. It does not explain what the tool returns, when it should be called, or what the parameters mean. The agent would have to guess or search elsewhere for the information needed to invoke it correctly.

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

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

Schema coverage is 0%, and the description mentions only 'listing_id' in the context of binding. Other parameters (name, kind, tags, tools, skills, register, description) are left entirely unexplained, so the description fails to compensate for the lack of schema documentation.

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 phrases the purpose as 'content-addressed capability hash', which is ambiguous—it's unclear whether 'hash' is the noun (a hash of a capability) or the verb (to hash a capability). The optional 'register + bind listing_id' hints at a secondary action but does not clarify the tool's core function. It fails to provide a specific verb and 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?

There is no guidance on when to use this tool versus siblings like match_capability or bind_identity. 'First principles' reads as a conceptual note rather than a usage condition. No exclusions, alternatives, or prerequisites are given.

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

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

With no annotations, the description must disclose behavioral traits but instead offers only abstract concepts ('signal freshness', 'outcomes'). It does not state whether the tool performs a read-only check, what side effects exist, or what inputs/outputs to expect. The absence of any concrete behavioral disclosure makes this inadequate.

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 single sentence is short but is under-specified to the point of being cryptic. It spends words on 'First principles' and jargon rather than conveying actionable information. This is not conciseness; it is a lack of substance.

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 2 parameters, no output schema, and no annotations. The description provides only a high-level principle and does not cover what the tool does, how to use it, what the return value is, or any constraints. It is completely inadequate for correct tool invocation.

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

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

Schema description coverage is 0%, and the description does not mention any of the parameters (listing_id, max_hours). It fails to explain what these parameters mean or how they relate to liveness evaluation. The description offers no semantic value beyond the bare 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 vaguely suggests the tool determines liveness from signal freshness, but it never states a concrete action like 'check' or 'verify'. It references 'stigmergy + probe + outcomes' without explaining what the tool does operationally. This is a vague purpose rather than a clear verb+resource statement.

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

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

No guidance is provided on when to use this tool versus alternatives like check_status or probe_clean. The description only contrasts with 'Dual calendar alone' but does not name alternative tools or usage contexts. There is no indication of prerequisites or appropriate 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 only reveals that the tool polls until a condition is met. It fails to disclose whether it modifies state, error handling, or idempotency. The phrase 'checks clean' is ambiguous.

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

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

The description is extremely short (one sentence), which is concise but lacks critical information needed for correct usage, making it under-specified.

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 3 undocumented parameters, no annotations, and no output schema, the description fails to provide sufficient context for the 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 0% and description does not explain any of the three parameters (id, name, listing_id). The agent receives no insight into which parameter corresponds to the listing or how to use them.

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

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

The description states 'Poll listing status until lane=active (checks clean)', which clearly indicates the tool polls a listing's status until it becomes active. It distinguishes from sibling tools like 'search_active' or 'probe_clean' by specifying a polling pattern.

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

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

No guidance on when to use this tool versus alternatives. It does not explain prerequisites or when polling is appropriate, leaving the agent without context on when to invoke it over 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?

Annotations are absent, so the description carries full responsibility for behavioral disclosure. It fails to mention whether the tool reads, writes, mutates state, requires permissions, or has side effects. This is a complete lack of 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 short, but it is under-specification rather than effective conciseness. The single sentence conveys almost no operational information, so it does not earn 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 absence of annotations, no output schema, and zero parameter coverage, the description must explain what the tool does, how to use it, and what to expect. Instead, it offers only a vague tagline, leaving the tool essentially undocumented.

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

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

Schema description coverage is 0% and the description does not mention either 'limit' or 'listing_id'. The description adds no meaning to the parameters, leaving their purpose entirely unexplained.

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

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

The description 'Composition interop — co-use peers + protocol endpoints' is vague and does not specify a concrete action or outcome. It fails to distinguish the tool from siblings like execute_compose or interop_resolve, and the meaning of 'co-use peers' is unclear.

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

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

No guidance is provided about when to use this tool versus alternatives. The sibling list includes potentially overlapping tools such as execute_compose and interop_resolve, but the description gives no exclusions or context.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does not disclose whether the tool is read-only, what it returns, side effects, or any operational context. There is no indication of what the output looks like or what 'probe/composition/Talk' means in terms of behavior. This is a severe lack of transparency.

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

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

The description is a single sentence with a dash and a parenthetical list. It is concise in word count, but the structure is cryptic and not self-explanatory. Every sentence should earn its place; this one conveys some information about cost categories but leaves the reader guessing about the tool's purpose. It is not well-structured for clarity, so a score of 3 is fair.

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

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

The tool has no output schema and no annotations, so the description is the only source of context. It is highly incomplete: it does not explain the output format, how 'free to replicate vs real cost' is determined, what the parenthetical examples mean, or what the user should expect from invoking the tool. The description is too thin to be considered complete even for a concept-heavy 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 tool has zero parameters and an empty input schema, so the schema description coverage is 100%. According to the rubric, with 0 params the baseline is 4. The description does not need to explain any parameter semantics since there are none, and it does not introduce any expectations about input. Therefore, a score of 4 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 'Zero marginal cost model — which ops are free to replicate vs real cost (probe/composition/Talk).' is a noun phrase without a clear action verb. It hints at a cost classification tool but does not explicitly state what the tool does (e.g., 'returns', 'lists', 'calculates'). It also does not distinguish it from sibling tools like zero_mc_pack or get_exonomics.

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

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

The description gives no explicit guidance on when to use this tool versus alternatives. It implies it might be used to understand cost implications of operations, but it does not state 'use this when...' or mention any exclusions or alternative tools. The mention of 'probe/composition/Talk' is cryptic and does not clarify the intended use case.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It mentions side effects like 'Raises O in V(N,C,O,F)' and 'refills free kernel/loop events', but these are opaque and not explained in terms of impact, permissions, or reversibility. The description fails to give a clear mental model of what side effects the agent should 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 short, with no filler words, and the key action is front-loaded in the first sentence. The second sentence packs in behavioral details in a compact way, though the cryptic notation reduces clarity. It is concise but not optimally structured for 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?

The tool has 8 parameters, no annotations, no output schema, and uses domain-specific jargon (V(N,C,O,F), WTP). The description is far from sufficient for an agent to correctly invoke the tool: it doesn't explain the meaning of key parameters, the context for 'real use', or what the expected return or side effects are. This level of incompleteness is significant for a tool with this 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 description coverage is low (13%: only 'quality' gets a description). The description mentions 'ok/latency/quality', which loosely maps to the `ok`, `latency_ms`, and `quality` parameters, but it doesn't clarify the meaning or format of `listing_id`, `listing_b`, `from`, `kind`, `body`, or how they relate to the described action. The description only partially compensates for the schema's lack of detail.

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 phrase 'Deposit ok/latency/quality after real use' gives a specific verb and resource, indicating the tool records outcome metrics. However, the rest of the description ('Raises O in V(N,C,O,F)', 'refills free kernel/loop events') is cryptic jargon that obscures the primary purpose and doesn't clearly differentiate it from siblings like leave_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 only implies usage 'after real use' but provides no explicit guidance on when to choose this tool over alternatives. There is no mention of exclusions, prerequisites, or comparisons to sibling tools such as leave_feedback or attest, leaving the agent without clear decision criteria.

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 must carry the full burden. It discloses the side effect of refilling mesh_match, which is good, but doesn't mention reversibility, authorization, or other behaviors. Some behavioral transparency exists, but not comprehensive.

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, no fluff, front-loads the primary purpose. Every word 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?

For a tool with 3 params, no annotations, and no output schema, the description gives the core purpose and a key side effect, but lacks details on optional params and usage boundaries. It's borderline 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 0%, and the description doesn't explain the optional 'body' or 'from' parameters. Only 'listing_id' is inferable from 'listing.' This is insufficient for correct invocation, especially for optional params.

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

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

The description clearly states the action 'Endorse a listing' and adds context with 'strong attraction' and 'refills free mesh_match.' It distinguishes from siblings by mentioning mesh_match, but the term 'strong attraction' is vague and could use clarification.

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?

Implies use case for reciprocity and refilling mesh_match, but doesn't explicitly state when to use vs alternatives or exclusions. Sibling tools like attest or leave_feedback could overlap, but no distinction is given.

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

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

With no annotations, the description carries the full burden but only mentions an abstract outcome (pipeline with endpoints and attestation). It does not disclose side effects, reversibility, security implications, or return format, leaving significant behavioral ambiguity.

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 text is short but not concise in a useful way; 'First principles:' adds no value and the sentence is too under-specified to be informative. It fails to earn its place as a tool description.

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 annotations, no output schema, and a 3-parameter schema lacking descriptions, the description is woefully incomplete. It does not explain input semantics, behavior, or expected output, making it inadequate for correct tool selection or invocation.

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

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

Schema coverage is 0% and the description offers no parameter explanations. The 'A→B' hint does not map to the actual parameters (from, listing_id, listing_b), so the agent has essentially no semantic guidance for constructing a valid invocation.

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 says it turns 'used_with composition' into an 'invocable A→B pipeline with endpoints + attestation,' giving a broad sense of transformation. However, the jargon and lack of concrete resource/verb clarity make it vague and difficult to distinguish from sibling tools like compose_peers or used_with.

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

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

No guidance is provided on when to use this tool versus alternatives. It references used_with composition but does not state prerequisites, exclusions, or typical scenarios, leaving the agent to guess.

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 fails to state whether the operation is read-only or mutating, what kind of output to expect, or any side effects (e.g., leaving a trace). The phrase 'follow' is ambiguous—could mean navigate, subscribe, or record—and no details are given about the underlying mechanism or safety profile.

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

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

The description is a single concise sentence, which is efficient and front-loaded with the action verb. However, the opening term 'Stigmergy' may be jargon that obscures rather than clarifies, and the sentence tries to compress multiple ideas (hottest trails, demand peaks, composition paths) into a compact form, sacrificing clarity for brevity.

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

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

Given the tool has 2 parameters, no output schema, and no annotations, the description is significantly incomplete. It does not explain the return format, pagination or limit behavior, when each kind is appropriate, or any prerequisites or side effects. The description only scratches the surface of what the tool likely does, leaving the agent with insufficient information for correct 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?

The schema has 0% description coverage, so the description must compensate. It partially explains the 'kind' parameter by associating enum values with concepts (hot → hottest trails, dangerous → danger, demand → demand peaks, composition → co-use paths), which is helpful. However, the 'limit' parameter is completely undocumented, and the relationship between 'attraction − danger' and the kinds is not precisely defined.

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 ('follow') and identifies resources ('hottest trails', 'demand peaks', 'composition co-use paths'), giving a clear sense of the tool's function. However, it does not explicitly differentiate from sibling tools, and the term 'Stigmergy' adds ambiguity rather than clarity. The mention of categories like 'attraction − danger' and different kinds helps distinguish the tool's scope.

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 by listing different trail types (hot, dangerous, demand, composition), suggesting the user can choose a kind. However, it does not provide explicit guidance on when to use this tool versus alternatives, nor does it mention any exclusions or prerequisites. The usage context is only partially 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?

With no annotations, the description must disclose behavioral traits. It implies a read operation via 'meter' and 'get', but does not explicitly state that it is read-only, side-effect-free, or requires any authorization. It also doesn't describe the return format or whether it could fail.

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

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

The description is a single sentence with no unnecessary words, but the phrasing is slightly convoluted ('multipliers that raise rates of match, conversion, outbound') and could be more direct. It is concise and front-loaded with the core term.

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 params, annotations, or output schema, the description is the only info. It names output components but doesn't specify types, units, or usage context, leaving gaps that could lead an agent to misuse the tool or misunderstand its 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?

The tool has zero parameters, so schema coverage is vacuous. The description adds value by explaining what the tool outputs (acceleration_index and multipliers), which compensates for the lack of parameter details and clarifies the tool's purpose.

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 identifies the tool as an 'Autocatalysis S-curve meter' and lists returned data (acceleration_index, multipliers), giving a sense of the resource. However, it uses domain-specific jargon and doesn't explicitly state an action like 'returns' or 'fetches', making the purpose somewhat ambiguous and not clearly distinguished from sibling tools like s_curve_board.

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

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

No guidance is provided on when to use this tool versus alternatives. The description is purely declarative and doesn't mention contexts, prerequisites, or exclusions, leaving the agent without criteria for selection.

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

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

No annotations are provided, so the description carries the full burden of disclosing behavioral traits. It does not explicitly state that this is a read-only operation, nor does it mention any side effects, authentication requirements, or limits on data retention. While a log retrieval implies safety, the description does not proactively disclose this.

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

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

The description is a single sentence that conveys the core functionality efficiently. However, it includes unexplained jargon ('Dual', 'Agent Runs-style observability') which slightly detracts from clarity. Overall, it is compact and front-loaded with the key purpose.

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, no output schema), the description adequately explains the return fields (duration, status, cost) and the scope (recent executions). It does not over-explain, and the schema fills in the parameter details. The description is sufficient for an agent to understand the tool's purpose without additional context.

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 covers the single parameter (limit) with 100% coverage, including its default and range. The description does not add any additional meaning to the parameter beyond what the schema already provides, 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 recent MCP/tool executions with duration, status, and cost. It uses a specific resource ('agent runs') and provides detail about the returned fields, making the purpose evident. However, it does not explicitly distinguish itself from sibling tools, and the term 'Dual' is somewhat ambiguous.

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 when you need to inspect recent run executions, but it provides no explicit guidance on when to use this tool versus alternatives, nor does it mention any exclusions or prerequisites. The usage context is understandable but not spelled out.

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

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

With no annotations provided, the description must carry the burden of behavioral disclosure. It only lists components (zero-MC cost model, V(N,C,O,F), hyper_index, stacked S-curves) but does not state whether the tool returns data, calculates values, has side effects, or what the output format is. This is a significant gap for a tool that appears to be a read-only status provider.

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

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

The description is a single, compact sentence that encodes several pieces of information efficiently. It is not padded with unnecessary words. However, the heavy use of abbreviations (MC, V(N,C,O,F)) makes it somewhat cryptic, but this does not detract from its brevity.

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

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

Given the tool has no output schema and no annotations, the description is expected to provide sufficient context about what is returned and why the listed components matter. It fails to explain 'zero-MC cost model', the meaning of V(N,C,O,F), what hyper_index is, or what 'stacked S-curves' represent. The description is incomplete for an agent to understand the tool's output or behavior without external knowledge.

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 zero parameters, so the baseline is 4 per the rubric. The description adds no parameter semantics but also does not need to compensate for missing schema information since there are no parameters to document. The listing of components is consistent with the tool's purpose but does not specifically enhance 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 'Exonomics status: zero-MC cost model + network value V(N,C,O,F) + hyper_index + stacked S-curves' gives a vague sense of providing a status report, but lacks a clear verb like 'retrieve' or 'calculate' to state what the tool actually does. It lists components rather than specifying an action, making it ambiguous whether this is a query, a computation, or something else. It does distinguish from siblings by naming specific exonomics metrics, but not clearly enough to earn a higher score.

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

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

There is no guidance on when to use this tool versus alternatives. It does not mention any conditions, prerequisites, or comparisons to sibling tools like hyper_index or network_value. The description simply states the content without any context on appropriate usage.

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

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

No annotations are provided, so the description carries the full burden of explaining behavior. It mentions a 'scarce-resource stigmergic heat signal' but does not disclose whether the tool is read-only, what side effects exist, or what the output represents.

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 very short and front-loaded, containing no fluff. However, the heavy jargon ('stigmergic heat signal') sacrifices clarity for brevity, making it less effective than a plain statement.

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, no annotations, and a simple no-param interface, the description should clearly explain the return value and use case. It fails to do so, offering only a cryptic metaphor that does not fully compensate for the missing structured metadata.

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 adds minimal extra meaning, but since there are no parameter semantics to document, this 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 lacks an explicit verb, so it does not clearly state what the tool does. 'Founding free seat meter (100 seats) + deal copy' hints at content but not the action, and the cryptic phrasing does not adequately distinguish it from sibling getter tools.

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

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

There is no guidance on when to use this tool versus alternatives. The description does not mention any context, prerequisite, or exclusion, leaving the agent to guess from the name alone.

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

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

No annotations are provided, and the description does not disclose behavior: it doesn't state that this is a read-only operation, what data is returned, format, or any constraints. The description is purely conceptual and leaves all behavioral aspects unspecified.

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

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

The description is a single short sentence, but it is phrased as a domain explanation rather than a tool spec. It is concise in length but lacks structural clarity; the philosophical framing and em dash detract from communicating the tool's function.

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 and no annotations, the description should explain the tool's return value and integration context. It only provides a high-level concept, leaving agents without knowledge of what they will receive or how to interpret the response.

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 zero parameters, so there is nothing to describe. The description adds no parameter detail, which is acceptable since no parameters exist. Per guidelines, a baseline of 4 is appropriate for a zero-parameter tool.

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

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

The description defines the incentive surface conceptually ('transparent incentive surface — founding seats, rank rules, liveness physics') but never states the tool's action (retrieving incentives). It implies that this tool exposes incentive data for planning, but the language is abstract and doesn't clearly distinguish it from siblings like get_exonomics or network_value.

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 offers a vague use case ('agents can plan against') but no explicit when-to-use or alternative guidance. It doesn't indicate when to prefer this tool over other economic/network tools, so usage is only implied.

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

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

With no annotations, the description carries the full burden. It adds context by noting it is 'aligned to the Vercel dashboard' and lists the cost components, but does not explicitly state side effects or safety (e.g., read-only, caching). For a simple get, this is adequate but not rich.

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, then usage. No redundant words 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?

Given no output schema, the description gives enough context about what is returned (cost total with components). It could mention the return format (e.g., a number or object), but for a no-parameter monitoring tool, the description is sufficiently 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 adds meaning by explaining what the tool computes, even though there are no parameters to document.

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 returns the Vercel Fluid cost total, specifying the components (Active CPU, Provisioned Memory, Invocations). It is specific to Vercel Fluid, which distinguishes it from generic cost tools, though it does not explicitly mention 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 'Use to monitor spend' provides a clear usage context. It tells the agent when to use this tool (for monitoring spend), but does not give exclusions or 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 are provided, yet the description does not disclose whether the tool performs reads or writes, requires authentication, or has side effects. The cryptic phrasing adds no behavioral clarity.

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

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

The description is short but not effectively concise—it sacrifices clarity for brevity, using jargon that obscures meaning rather than aiding understanding.

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 lack of output schema, annotations, and parameter documentation, the description is severely incomplete. An AI agent cannot reliably determine input, output, or appropriate usage from this text.

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

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

Schema description coverage is 0% and the description only mentions 'listing (or URL)' without explaining any of the three parameters (url, name, listing_id) or how they relate to the tool's function.

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 unclear terminology ('Dual', 'portable clean badge URL') and fails to specify a clear verb-resource relationship. It hints at checking reciprocity trust but does not define what that means or how the tool accomplishes it.

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

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

No guidance is given on when to use this tool versus siblings like probe_clean or check_status. The description does not specify prerequisites, intended context, or 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?

No annotations are present, so the description carries the full burden of disclosing behavior. It only states a formula, with no mention of side effects, read-only guarantees, rate limits, or return values. This leaves the agent completely in the dark about invocation consequences.

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 very short but also cryptic and under-specified. It reads like a fragment, sacrificing clarity for brevity. It is not well-structured and leaves out key 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?

With no output schema and a three-line definition, the description fails to provide enough context for an agent to understand what this tool does, when to call it, or what to expect in return. It is not complete even for a simple conceptual 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 has zero parameters, so the baseline is 4. The description does not need to explain parameters since there are none, and it does not contradict 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 gives a mathematical formula for hyper_index rather than stating an action or purpose. It lacks a verb like 'compute' or 'return', so it's unclear what the tool actually does. It doesn't distinguish itself from sibling tools like get_acceleration.

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

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

No guidance is provided on when to use this tool or how it relates to alternatives. The description is purely definitional and gives no context for selection.

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

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

With no annotations, the description carries the full burden. It does disclose the free allowance, pay-per-run cost, and return of 'system_prompt_short + Network Edition', but it omits side effects, required permissions, whether it modifies state, or response structure. This is insufficient for a tool with payment implications.

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

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

The description is short and front-loaded, with the main facts (free quota, pricing, return summary) succinctly presented. However, 'ONE-CALL value' is marketing filler, and the overall message is somewhat vague despite its brevity.

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

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

Given 6 parameters, no annotations, no output schema, and a presumably nontrivial operation (improving a kernel), the description is far from complete. It leaves major unknowns about invocation, parameter meanings, expected outputs, and limitations, making it difficult for an agent to use correctly.

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

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

Schema coverage is only 33% (goals and payment_proof have descriptions), and the description compensates minimally. It loosely connects 'goals' to the goals parameter and mentions system_prompt_short as an output, but the critical parameters agent_name, listing_id, domain, and current_prompt are left unexplained. The description adds little value 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 is largely a restatement of the tool's name ('Kernel Improver') and focuses on pricing and return values rather than the specific function. It does not clearly explain what 'improve' means, how it uses inputs like current_prompt/domain, or differentiate it from the many sibling tools.

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

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

The description mentions 'no demo order required' and free/pay-per-run allowances, which hints at an immediate-use context, but it does not explicitly say when to use this tool versus alternatives or when not to use it. No exclusions or alternative tool mentions are 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?

With no annotations, the description carries full responsibility for behavioral disclosure. It only describes the high-level purpose without mentioning side effects, output format, prerequisites, or whether it's read-only. The phrase 'find and how to invoke' hints at discovery but doesn't detail 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?

A single sentence that is front-loaded and contains no filler. Every word contributes to stating the tool's purpose and protocol scope.

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 6-parameter tool with no output schema and no annotations, the description is insufficient. It gives a high-level purpose but does not explain how to construct a query, what 'capability nodes' are, or what the response contains. The description is not complete enough to guide correct 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 low (17%), only 'q' has a description. The tool description adds some meaning by mentioning protocols, which helps interpret 'prefer', but it doesn't explain 'tool', 'skill', 'listing_id', or 'limit'. The description fails to compensate for the undocumented parameters.

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

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

The description clearly states a specific action ('resolve') and resource ('capability nodes') with protocol scope (MCP/A2A/ARD/HTTP). It distinguishes from siblings like ard_search (single protocol) and interop_session (session management), though it doesn't explicitly name 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?

No guidance on when to use this tool vs alternatives. It implies cross-protocol scenarios but doesn't state exclusions or compare with matching tools like match_capability or hyper_index. The description lacks 'use this when' or 'instead of' cues.

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 disclosing behavior. It does reveal a notable trait: sessions survive MCP or A2A entry, and it outlines a lifecycle (match → demo → feedback). However, it omits details about the 'get' action, side effects of open vs append, and any required setup or permissions, so transparency is only partial.

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

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

The description is a single, concise sentence that packs in the core action, the session lifecycle, and the cross-protocol persistence trait. There is no fluff, and the most important information is front-loaded.

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 (10 optional parameters, no annotations, and no output schema), the description is severely under-specified. It does not clarify the meaning of many parameters, the behavior of the 'get' action, or what the tool returns, leaving an agent with insufficient information to use it correctly.

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

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

Schema description coverage is 0%, and there are 10 parameters. The description helps infer a few parameters: 'match → demo → feedback' maps to match_q, demo_order_id, and feedback_id, while 'MCP or A2A entry' maps to entry_protocol. But it does not explain other important parameters like session_id, agent_name, listing_id, detail, step_action, or the 'get' action, leaving significant gaps.

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: 'Open or append a cross-protocol session'. It uses a specific verb-resource pair and adds valuable context about the session lifecycle (match → demo → feedback) and that it survives MCP or A2A entry, distinguishing it from sibling tools like interop_resolve or take_demo.

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

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

There is no explicit guidance on when to use this tool versus alternatives. The description implies usage for cross-protocol session management, but it does not mention any exclusions, prerequisites, or comparisons to sibling tools, leaving the agent to infer appropriate usage.

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

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

With no annotations provided, the description must disclose side effects and behavioral traits. It implies a compound operation (listing, hashing, joining, session, template) but does not state whether it mutates state, requires authentication, or has irreversible effects. The phrase 'One hop' is metaphorical and unclear.

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

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

The description is a single concise sentence, but it sacrifices clarity for brevity. For a tool with six parameters and nested objects, this cryptic chain-of-arrows is under-specified and does not structure information in a way that helps the agent understand the tool's purpose or usage.

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 fails to cover essential context: no return value explanation (no output schema), no side effects, no prerequisites, no error behavior, and no relationship to sibling tools. The complexity (6 params, nested objects) demands a much fuller description to be minimally usable.

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 33% description coverage, and the tool description adds nothing about parameters. It references 'cap_hash' and 'outcome template' but does not map them to url, name, source, server_json, or agent_card_url. The agent cannot infer how to fill the six parameters from the description.

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

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

The description 'Compound self-serve: list (optional) → cap_hash → joined trail → interop session → outcome template' hints at a multi-step workflow but never states a clear verb+resource. The name suggests joining/contributing, but the description does not explicitly say what the tool ultimately does or what a successful invocation achieves.

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

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

There is no guidance on when to use this tool versus alternatives like interop_session, list_yourself, or follow_trail. The description does not mention any prerequisites, exclusions, or alternative tools, leaving the agent without context for choosing this over 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 carries the full burden. It discloses that feedback is optional and not required for allowance, and it mentions an incentive for early users. However, it doesn't describe the actual effect of submitting feedback (e.g., data handling, side effects, or whether it is a write operation), leaving a significant transparency gap.

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 sentences long and front-loaded with the core purpose. The first sentence is clear, the second adds relevant optionality, and the third provides motivational context. It is concise, though the third sentence is slightly tangential to tool usage.

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 9 parameters, no annotations, and no output schema, the description is too sparse. It doesn't explain what structured feedback includes, how to set ratings, what the 'answers' object should contain, or any expected outcomes. The tool is moderately complex, so the description should do much more to fill these 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?

The schema has 9 parameters with 0% description coverage, and the description adds no parameter-level information. Even the required 'agent_name' is not mentioned, and complex parameters like 'answers' and 'rating' are left to the agent's interpretation. The description fails to compensate for the low 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 identifies the tool as leaving structured feedback after trying value tools or a demo. It uses a specific verb ('leave') and resource ('feedback'), and it is distinct from all sibling tools which focus on search, composition, networking, and other operations.

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 states when to use the tool ('after you tried value tools or a demo') and explicitly clarifies it is never required for the free event allowance. While it doesn't mention alternatives, the tool is unique in its purpose, so the context is sufficient.

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

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

The description discloses two key behaviors: it 'refills free mesh_match (reciprocity)' and other agents sense it via specific tools. This adds meaningful side-effect context beyond the schema. However, with no annotations and no mention of persistence, reversibility, permissions, or lifecycle of the trace, the disclosure is incomplete.

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 convey the core purpose, a behavioral effect, and how others interact with the trace. No filler or repetition. The reliance on jargon ('Stigmergy') slightly reduces clarity, but the structure is efficient and front-loaded.

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 provides a conceptual overview but is incomplete for a tool with 6 optional parameters, no output schema, and no annotations. It lacks information about return values, kind-specific behavior, intensity semantics, tags usage, and error conditions, leaving an autonomous agent under-informed for reliable invocation.

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

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

Schema description coverage is only 33%, and the description does not elaborate on any parameters. It fails to explain what body, from, kind, tags, intensity, or listing_id are used for, nor how the reported effects map to them. The schema's enum and defaults provide basic info, but the description adds no parameter-level semantics.

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

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

The description opens with 'Stigmergy mark on Dual', which indicates leaving a trace in the environment and distinguishes the tool from sensing tools like sense_traces and follow_trail. However, the term 'Stigmergy' is niche and 'Dual' is undefined, so the purpose is partially obscured by jargon.

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 on when to use leave_trace versus alternatives like endorse, leave_feedback, or attest. The description only mentions that it refills mesh_match and that others sense via sense_traces/follow_trail, implying a communication mechanism but not providing direct comparison or 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?

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It only states what the tool lists, without explicitly saying it is read-only, side-effect-free, or disclosing any permissions or constraints. The phrase 'reciprocity refill policy' hints at a policy rule but does not clarify mutability or safety.

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

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

The description is a single concise sentence that front-loads the main purpose ('List event prices...') and uses no filler words. Every word earns its place, and it is appropriately sized for a simple read-only listing tool.

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

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

For a tool with no parameters and no output schema, the description adequately covers the scope of what is returned (prices, allowances, policy). While it does not elaborate on the format of the output, the simplicity of the operation makes this acceptable. The three listed items give sufficient context for an agent to decide to call it.

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, and the schema coverage is 100% (empty schema). According to the rubric, a baseline of 4 is appropriate when no parameters exist. The description does not need to add parameter details since there are none.

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 the specific verb 'List' with a clear resource ('event prices, free daily allowances, and reciprocity refill policy'). It clearly identifies what the tool returns and distinguishes itself from sibling tools like get_reciprocity or get_incentives by focusing on event pricing specifically.

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

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

The description provides no guidance on when to use this tool versus alternatives. It does not mention any context, exclusions, or alternative tools, leaving the agent without explicit direction on choosing this over sibling tools like get_reciprocity.

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?

Discloses the probe-and-activate behavior and a time estimate of 6 minutes. However, with no annotations, the description should also mention auth requirements, rate limits, or data handling; these are absent.

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

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

The description is short but includes an unrelated promotional phrase. It could be more focused on functionality and remove the marketing language to be truly concise.

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 6 parameters, no output schema, and sibling tools for different purposes, the description should clarify return values, how to use extra parameters, and the 'demo+feedback' unlock condition. It leaves significant 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 only 33% (only 'url' described). The description mentions 'POST card/server URL' but does not explain parameters like 'name', 'source', 'server_json', etc. The description adds little 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 states the tool is for self-listing by posting a card/server URL, then probing until active. This distinguishes it from sibling tools like 'search_active' or 'check_status'. However, the promotional phrase about demo/feedback detracts from clarity.

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

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

No explicit guidance on when to use this tool versus alternatives like 'ard_search' or 'match_capability'. The description only implies it's for initial self-registration but lacks comparative 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 the full disclosure burden. It does expose a meaningful behavioral trait—ranking includes stigmergic usage pheromones—but it doesn't clarify potential side effects, return behavior, or any limitations beyond that trait.

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 tight sentences, front-loaded with the core purpose and then adding a meaningful detail about ranking behavior. No word is wasted.

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 four parameters, two enums, no output schema, and no annotations, the description is too thin to fully guide correct invocation. It does not explain federation modes, limit semantics, or the structure/shape of the ranked results.

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

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

Schema description coverage is only 25% (only 'q' is explained). The tool description does not compensate for the undocumented 'kind', 'limit', and 'federation' parameters, leaving their semantics and enum meanings unclear.

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 ranks Active clean listings for a natural-language need, using a specific verb and resource. It also hints at a distinguishing ranking mechanism ('stigmergic usage pheromones'), though it doesn't 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 description implies the use case: when you have a natural-language capability need. However, it does not provide explicit when-not-to-use guidance or mention alternatives like search_active, so usage guidance is present but not fully realized.

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 full responsibility for behavioral disclosure, yet it says nothing about side effects, permissions, changes to the server, or what the tool actually does beyond the 'pack' metaphor. The only behavioral hint is the free-then-paid pricing model, which is a cost constraint rather than an operational 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 very brief, but brevity here is under-specification, not conciseness. The two sentences are mostly marketing and pricing information, with no functional structure or priority given to explaining what the tool does.

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

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

For a tool with six parameters, no annotations, no output schema, and a vague purpose, the description is severely incomplete. It fails to provide the minimal context needed for an agent to select or invoke the tool correctly, leaving the entire semantic burden on the sparse 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 only 17% (1 of 6 parameters), and the description itself adds no parameter-level context. All six parameters are optional and mostly undocumented, so an agent has no way to infer what values to provide or how they affect the composition.

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 vaguely identifies the tool as a 'MCP Mesh composition / tool_policy pack' but does not state a clear verb or specific action. It reads more like a product slogan than a functional definition, and it does not distinguish this from siblings like execute_compose or compose_peers.

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

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

No guidance is provided on when to use this tool versus alternatives. The phrase 'ONE-CALL' hints at a convenience factor, but there is no mention of prerequisites, exclusions, or comparison with similar composition/peering 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?

The description discloses cost behavior (free tier and per-match fee) but nothing else. It does not mention whether the operation is read-only, what it returns, or any side effects. With no annotations provided, this leaves significant behavioral ambiguity.

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. Each sentence adds information (purpose, pricing, a caveat), but the 'No demo order' phrase is cryptic and could be misinterpreted, slightly reducing clarity.

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

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

With six parameters, no required fields, no output schema, and no annotations, the description is insufficient for correct invocation. It does not explain what inputs are needed, how to supply payment_proof, or what the response will look like.

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 only 17% (just 'capabilities' has a description). The tool description does not explain any of the six parameters (goals, limit, agent_name, listing_id, payment_proof), so it fails to compensate for the low 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: 'rank complementary Live agents/MCPs for your capabilities.' It uses a specific verb ('rank') and identifies the resource (complementary agents/MCPs) and the input scope (your capabilities), distinguishing it from siblings like match_capability that likely focus on direct matching rather than ranking complements.

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

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

The description provides no guidance on when to use this tool versus alternatives. It mentions 'Free 5/day then $0.10/match' and 'No demo order,' but these are pricing/format notes, not usage context. There is no mention of prerequisites, scenarios, or 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'near-zero free' (suggesting low cost) and 'snapshot' (possibly implying read-only), but it does not state side effects, permissions, return format, or state changes. The cost hint is valuable, but the overall behavior is still opaque.

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

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

The description is extremely short and front-loaded, but its brevity comes at the cost of clarity. 'Near-zero free: sense_traces + follow_trail snapshot (Network Edition)' and 'Prefer before re-probe' are cryptic phrases that underspecify the tool rather than efficiently conveying 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 two parameters, no output schema, no annotations, and no parameter descriptions, the description must provide substantial context. It does not explain the return value, how the snapshot is composed from sense_traces and follow_trail, or how to filter results, making it inadequate for safe and correct 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?

The input schema has zero parameter descriptions (0% coverage), and the description does not mention 'limit' or 'listing_id' at all. It fails to explain what these parameters control or how they affect the snapshot, so there is no compensation for the schema's lack of detail.

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 reads 'sense_traces + follow_trail snapshot (Network Edition)' but never states what the tool actually does, such as retrieving or listing data. It mentions a 'snapshot' but lacks a specific verb and resource, leaving the purpose ambiguous. It does distinguish a 'Network Edition' scope, but the core function remains unclear.

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 only guideline is 'Prefer before re-probe', which is vague and undefined—there is no explanation of what 're-probe' means or when this tool should be chosen over sibling tools like sense_traces or follow_trail. It gives a preference hint but lacks explicit when-to-use versus alternative 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?

No annotations are present, so the description must bear the full burden of disclosing behavior. It states the metric formula and optional overrides but does not mention whether the operation is read-only, requires permissions, produces side effects, or returns values. The 'meter' wording hints at a non-mutating calculation but lacks explicit behavioral guarantees.

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

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

The description is a single, front-loaded sentence with no filler. The formula is compactly presented and the optional override note is integrated efficiently, making it appropriately sized for the tool's apparent simplicity.

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 there is no output schema, no annotations, and no parameter descriptions, the description should provide richer context to compensate. It covers the formula and a planning use case, but leaves input semantics, output format, and edge cases unaddressed, making it only minimally 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?

With 0% schema description coverage, the description needed to explain all parameters. It mentions N, C, O, and F as components of the formula, giving them some role, but does not define what they represent, their units, defaults, or how override works. 'dense' is entirely unexplained.

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

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

The description identifies the tool as a 'Superlinear network value meter' and provides the formula V ∝ N^α · C^β · O^γ · F^δ, clearly indicating it computes a network value metric. It does not explicitly name an action verb or contrast with sibling tools, but the formula and 'meter' make the purpose reasonably distinctive.

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 'Optional N/C/O/F override for planning' implies a planning use case and indicates the tool accepts overrides, but it does not specify when to use this tool versus alternatives or provide exclusions. The usage context is implied rather than explicitly stated.

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

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

With no annotations, the description carries the full burden. It discloses a behavioral side effect: 'Fail deposits danger pheromone; ok dampens danger', which informs that the tool is not purely read-only. However, the nature of 'danger pheromone' and 'dampens danger' is left undefined, so the disclosure is incomplete and cryptic.

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

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

The description is a single sentence that is concise and does not waste words. It front-loads the primary purpose ('return Dual clean-registry status') and adds a behavioral note. However, the brevity contributes to ambiguity, but that is a clarity issue rather than a conciseness issue.

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

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

The tool has no output schema, no annotations, and unclear parameters. The description mentions a side effect and a status return but omits essential details about parameter meanings, output format, and what 'danger pheromone' entails. For a tool with this complexity, the description is significantly incomplete.

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 3 parameters (id, name, listing_id) with 0% description coverage, and the tool description provides no explanation of what these parameters represent or how they are used. The description fails to compensate for the missing parameter documentation.

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 clear verb 'return' and a resource ('Dual clean-registry status'), so it is not a tautology. However, the resource is vaguely described with cryptic terms like 'Dual clean-registry' and no differentiation from sibling tools such as check_status or check_liveness.

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

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

The description provides no guidance on when to use this tool versus alternatives. There is no mention of conditions, prerequisites, or exclusions. The phrase 'Probe-as-service signal' gives only a weak hint of its role as a probe, but no actionable usage context.

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

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

With no annotations, the description carries the full burden. It discloses cost/rate limits ('Free 3/day then $0.25/tick') and mentions the return ('next phase + measurable actions'). However, it does not disclose side effects, required inputs, or what happens if payment_proof is missing. It provides some useful behavioral context but leaves significant gaps.

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 key value proposition. It packs pricing and return expectations into a short space. However, the term 'ONE-CALL value' is marketing jargon, and the sentence structure is a bit choppy, but overall it is efficiently written.

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

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

Given the tool has 5 parameters including an object type, no output schema, and zero parameter descriptions, the description is extremely incomplete. It only covers cost and a vague return type, leaving the agent without necessary information to correctly construct inputs or interpret results. This is inadequate for a tool of this 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 description coverage is 0%, and the description does not explain any of the five parameters (goals, agent_name, listing_id, prior_state, payment_proof). The required agent_name is unexplained, and the prior_state object is opaque. The description adds no value beyond the bare 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 states the tool performs 'one Recursive Loop improvement cycle' and returns 'next phase + measurable actions', which is a specific action with a resource. It also distinguishes from a demo order, giving some differentiation from sibling tools like take_demo. However, the jargon 'ONE-CALL value' and 'Recursive Loop' is not explained, slightly reducing clarity.

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

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

The description provides no explicit when-to-use guidance or alternatives. The phrase 'no demo order' implies it is a standalone quick action, but it does not mention when to prefer this over other loop-related tools like improve_kernel or take_demo. Pricing info (free 3/day, then $0.25/tick) is cost context, not usage 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 provided, the description must carry the full burden of behavioral disclosure. It only names a dashboard and topic areas, without revealing side effects, return format, or whether it is read-only. This falls short of disclosing 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 a single short sentence, but it is a fragment that lists topics rather than a complete sentence. It is concise in length but under-specified in substance, so it does not fully earn 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?

The tool has no output schema and no annotations, so the description is the sole source of context. It fails to explain the purpose, behavior, or context, making it inadequate for an agent to select or invoke 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 has no properties, so the description is not required to explain parameters. The 0-parameter baseline applies, and the description does not need to add anything about parameter semantics.

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

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

The description is a noun phrase ('Stacked S-curve dashboard') without an explicit verb, making the action ambiguous. It lists content areas (listings, trails, compositions, etc.) but does not state whether it retrieves, displays, or generates something, failing to distinguish it from sibling tools.

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

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

There is no guidance on when to use this tool versus alternatives. The description does not mention any prerequisites, exclusions, or alternative tools, leaving the agent without context for tool selection.

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

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

No annotations are provided, so the description carries the burden of disclosure. It reveals the HTTP method GET, which strongly implies a read-only operation, and mentions 'checks-clean' as a qualifier. However, it doesn't explicitly state side-effect-free behavior, auth requirements, or pagination details, leaving some ambiguity.

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

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

The description is a single concise sentence that front-loads the purpose and includes the API endpoint. It saves words but the parenthetical '(checks-clean)' is slightly unclear, yet overall it is efficient and not overly verbose.

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 search tool with three optional params and no output schema, the description provides a minimal but functional overview. However, it doesn't clarify the meaning of 'checks-clean', response format, or how results are limited/paginated, leaving some gaps for an agent.

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 three parameters (q, kind, limit) with descriptions, achieving 100% coverage. The tool description does not add extra parameter explanation, but this is acceptable given the schema already fully documents them.

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

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

The description starts with 'Search Dual Registry Active (checks-clean) agents + MCPs', giving a specific verb and resource, and includes the exact API endpoint. This clearly identifies the tool's function, though it doesn't explicitly contrast it with sibling tools like 'ard_search'.

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 this tool is for searching active agents and MCPs from the Dual Registry, but it lacks explicit instructions on when to use it over other search tools or any exclusion scenarios. The scope 'Active' gives some context, but no clear 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states that the tool seeds edges from Active clean clusters and avoids live re-probes, but does not mention whether edges are added idempotently, what permissions are required, or what side effects occur beyond opening the gate.

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

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

The description is extremely compact, using two clauses to convey purpose, source, and outcome with no filler words. However, the heavy use of domain jargon ('Near-zero bootstrap', 'composition_density gate', 'Active clean') reduces clarity despite the brevity.

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

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

For a single-parameter bootstrap operation, the description covers the purpose, data source, benefit, and system-level effect. It lacks a description of return values and does not explain the 'composition_density gate' concept, but the tool is simple enough that this is reasonably 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 single parameter max_pairs is fully documented in the schema with a description and default value, so the schema already provides complete parameter semantics. The tool description adds no additional parameter details, justifying the baseline score 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 specifies the action 'seed' with the resource 'used_with composition edges' and the source 'Active clean category/tag clusters', distinguishing it from query tools like used_with and probe tools like probe_clean. However, terms like 'composition_density gate' are unexplained, making the purpose less crisp than ideal.

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 'Near-zero bootstrap' and 'without live re-probes' imply a low-cost initialization use case, but there is no explicit when-to-use or when-not-to-use guidance versus sibling tools such as probe_clean or compose_peers. The context is inferred rather than clearly stated.

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

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

With no annotations, the description carries the full transparency burden. It does disclose a key side effect ('Evaporation applied on read'), which indicates the operation mutates state despite being a read. However, it omits other behavioral details like permissions, rate limits, or what evaporation means for subsequent reads.

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 with no filler. It front-loads the core action and adds the important evaporation caveat in the second sentence. The only minor issue is the unexplained 'Stigmergy' jargon, but it does not waste space.

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 absence of annotations and output schema, plus three undocumented parameters, the description is too minimal. It leaves 'Dual', 'pheromone trails', 'agent marks', and return behavior undefined, making it hard for an agent to invoke correctly in a broader workflow.

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

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

Schema description coverage is 0% and the description does not mention q, limit, or listing_id at all. The agent is left to guess the meaning of these parameters, with no compensation from the prose.

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 an explicit action ('read') and a concrete resource ('pheromone trails + agent marks on Dual'), clearly distinguishing it from siblings like follow_trail or leave_trace. 'Evaporation applied on read' adds a specific operational nuance that further defines the tool's behavior.

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

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

No guidance is given about when to use this tool versus alternatives such as follow_trail, leave_trace, or attest. The 'Stigmergy' intro implies a context but does not state exclusions or preferred 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?

No annotations are provided, so the description carries the full burden. It discloses side effects like depositing 'attraction pheromone' and counting toward 'founding free seats after feedback,' but it doesn't clarify whether this is a read-only or mutating operation, what permissions are needed, or any rates/limits. The behavioral traits are mentioned but vaguely.

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 at three sentences and front-loads the primary purpose. However, the cryptic jargon ('Kernel/Loop (or Mesh)', 'attraction pheromone') makes it less accessible, though each sentence serves a distinct purpose (purpose, parameter preference, side effect).

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

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

Given the tool has 5 parameters, no output schema, and no annotations, the description is inadequate for full comprehension. It doesn't explain return values, parameter semantics, or the exact workflow, making it difficult for an agent to invoke the tool correctly without additional context.

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 0% schema description coverage, the description must explain all 5 parameters, but it only mentions a preference for listing_id. The meanings of name, goals, mcp_url, and agent_card_url are entirely unexplained, leaving the agent to guess their roles in the demo process.

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

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

The description states the tool provides a 'Free Kernel/Loop (or Mesh) demo for an Active listing,' which is a specific purpose, but the metaphorical language ('Deposits attraction pheromone') and unclear terms like 'Kernel/Loop' obscure the actual function. It doesn't clearly distinguish itself from sibling tools beyond the demo focus.

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 only usage hint is 'Prefer listing_id,' which suggests a preferred parameter but doesn't explain when to use this tool versus alternatives or when not to use it. No explicit prerequisites or exclusions are provided, leaving the agent to infer the intended use case.

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

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

With no annotations, the description carries the full burden. It discloses that the tool records a co-use and builds a graph, but it does not mention whether the operation is idempotent, whether duplicates are allowed, any required permissions, or the data retention implications. For a mutation tool, this is a significant transparency gap.

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

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

The description is extremely concise—two short sentences with no filler. It front-loads the core purpose ('record that listing_a was used with listing_b') and adds the graph-building context in a compact way. Every word 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?

For a tool with 4 parameters and no output schema, the description is too sparse. It fails to explain the body and from parameters, does not mention what the tool returns, and provides no usage examples or broader context about the composition trail. The absence of annotations makes this completeness gap more impactful.

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 50%; listing_id and listing_b have descriptions, but body and from are undocumented in both schema and description. The description clarifies the relationship between listing_id and listing_b ('used with') but does not help understand the remaining parameters. Thus, it only partially compensates for the low 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 action ('record that listing_a was used with listing_b') and the resource (the co-use relationship). The 'Builds co-use graph' phrase adds context on the tool's effect. It is specific enough to distinguish from sibling tools like 'compose_peers' or 'execute_compose'.

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 composition tracking via 'Stigmergy: composition trail', but it does not explicitly state when to use this tool versus alternatives or mention any exclusions/prerequisites. No explicit when/when-not 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?

With no annotations, the description carries full responsibility for behavioral disclosure. It mentions verification of both JWS and ledger, but does not explain success/failure behavior, whether external calls are made, or permission requirements.

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

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

The description is a single sentence with no wasteful words, but 'First principles' is filler that adds no value. It is concise but lacks substance needed for effective use.

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 two parameters and no output schema, yet the description omits return values, error modes, and parameter details. This makes it incomplete for an AI agent to reliably select and invoke the 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 is 0%, and the description does not explain the 'id' parameter. It only hints that 'jws' relates to the JWS part of the attestation, but fails to map parameters to their roles or formats.

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: verifying a Dual-issued signed attestation using JWS and ledger. The verb 'verify' and specific object distinguish it from creation tools like 'attest' and 'endorse'.

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

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

No guidance is provided on when to use this tool versus alternatives such as check_liveness or check_status. There is no mention of prerequisites, exclusions, or preferred contexts.

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 exist, so the description carries the full burden of behavioral disclosure. It reveals the contents (caps + attestations) and a benefit (avoiding re-crawling), but does not state whether the call is read-only, what it returns, what side effects occur, or what prerequisites exist.

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

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

The description is a single short sentence, which avoids verbosity, but it is under-specified rather than efficiently informative. It omits the action, parameter semantics, and enough context to use the tool confidently.

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, no annotations, and a cryptic one-line description, the agent cannot determine what a successful call returns or how to handle the response. The modest complexity of a single optional parameter does not compensate for the missing behavioral and output information.

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

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

The schema has a single parameter, limit, with 0% description coverage. The description does not mention limit at all or explain how it controls the pack (e.g., maximum number of caps or attestations), leaving the agent to guess from the default value alone.

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 identifies a resource (Zero-MC federation pack) and an outcome (copying content-addressed caps + attestations without re-crawling Dual), but does not state an explicit action verb such as 'returns', 'creates', or 'downloads'. It is not a pure tautology, but the purpose remains vague because the primary operation is left implicit.

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 'to copy without re-crawling Dual' provides an implied use case, indicating when this pack might be needed. However, there is no explicit guidance on when to prefer this tool over sibling tools like attest, capability_hash, or verify_attestation, nor any exclusion criteria.

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