aegis

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

With no annotations, the description carries the full burden and does well: it discloses that it costs nothing, performs no probe and no spend, and relies on stored verification signals only. It stops short of covering auth, rate limits, or failure modes, but the safety/cost profile an agent needs for a preflight tool is clear.

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?

Front-loads the key qualification (FREE, preflight, before you pay) and the field list is compact. The trailing 'Free.' repeats information already stated in the opening, which is the one wasted token.

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?

There is no output schema, so the description usefully enumerates the returned signals (registered?, payment-worthiness, confidence, coverage, reasons, evidence). Combined with the sibling contrast, an agent has enough to call it correctly, though the url parameter's expected shape remains unstated.

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% with a single required 'url' parameter, so the description should compensate. 'THIS endpoint' loosely implies the url is the endpoint being verified, but it never states the format or whether it accepts a bare host, full URL, or identifier, leaving the parameter essentially undocumented.

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

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

States a specific action (preflight check) on a specific resource (an endpoint before payment) and explicitly contrasts it with the sibling trust_check, which it calls the paid version. An agent can distinguish it from trust_check, discover, and route without opening any schema.

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

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

Explicitly positions itself as the top of the funnel to use BEFORE paying and before the paid trust_check, which is named as the alternative that adds a fresh probe pass and ERC-8004 reputation. The when-to-use condition is stated directly rather than 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 of behavioral disclosure. It adds two traits: 'ranked by verification-backed trust' and 'Free', but does not state whether the operation is read-only, whether authentication is required, how results are paginated, or any potential side effects. For a search tool this is a notable 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 sentences, each contributing value. It efficiently communicates the core function and a key differentiator ('Free') without redundancy.

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

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

Given three undocumented parameters, no output schema, and no annotations, the description is insufficient. It does not clarify expected result format, filter semantics, trust thresholds, or how this relates to sibling tools. Users are left with significant uncertainty about how to invoke the tool effectively.

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

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

The input schema provides three parameters (query, category, min_trust) with zero description coverage. The description does not explain any of these parameters, their formats, allowed values, or how they influence the search. Since schema coverage is 0%, the description was expected to compensate but 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 clearly states the tool's function: 'Search the Aegis registry of agent-payable services, ranked by verification-backed trust.' This provides a specific verb (Search), resource (Aegis registry), and distinct method (ranked by trust). However, it does not differentiate from the sibling tool 'smart_discover', which likely surfaces similar registry data.

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

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

The description offers no guidance on when to use this tool versus alternatives like 'smart_discover' or 'trust_check'. The only contextual hint is 'Free', which implies a cost benefit but does not clarify selection criteria, necessary conditions, 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 burden of disclosing behavioral traits. It discloses the $0.005 payment via x402, which is a critical side effect, and mentions the Aegis probe cross-check and divergence flag. However, it does not state whether the operation is read-only, what the divergence flag represents, or how failures (e.g., unregistered agent) are handled.

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, consisting of two sentences that are front-loaded with the primary purpose. The payment information is included as a separate sentence, which is important and earns its place. The style is slightly noun-heavy, lacking a direct verb, but there is no wasted wording. It could be improved by starting with 'Get' or 'Fetch.'

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 annotations and output schema, and the sparse parameter documentation, the description is not complete enough. It explains what the tool does at a high level and notes the cost, but it does not describe the return value, the exact meaning of parameters, or edge-case behavior. An agent would need more information to invoke this tool correctly, especially regarding the 'domain' parameter.

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 two parameters, domain and agent_id, with zero description coverage (0%). The description does not explain either parameter explicitly. It hints that 'agent_id' corresponds to an agent in the Base IdentityRegistry, but 'domain' remains ambiguous. With no schema descriptions, the description should compensate but does not provide sufficient per-parameter meaning.

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

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

The description clearly identifies the tool as providing on-chain ERC-8004 reputation for agents on the Base IdentityRegistry, plus an Aegis probe cross-check and divergence flag. It lacks an explicit verb like 'Get' or 'Fetch,' but the noun-phrase style still conveys the purpose. It distinguishes from siblings by referencing ERC-8004 and Aegis, though it doesn't explicitly compare to 'trust_check.'

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 mentions 'any registered agent' and a payment requirement, but it does not state scenarios where this should be preferred over sibling tools such as 'trust_check' or 'discover.' It only implies that it is used when ERC-8004 reputation is needed.

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 discloses several key behaviors: service selection, execution with failover, payment only on delivery, signed receipt, and budget enforcement ('Never over budget'). This goes beyond basic mutation but does not cover potential errors, auth, or rate limits.

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 two sentences, front-loading the purpose with 'TASK+BUDGET procurement'. While it includes jargon ('Aegis', 'x402', '_meta') that may require prior knowledge, every sentence contributes valuable information about behavior and constraints.

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 2-parameter tool with no output schema, the description is relatively complete. It indicates the return value ('returns data + Ed25519-signed receipt') and key behavioral guarantees. However, 'data' is vague, and the term 'x402 via _meta' is unexplained, leaving some gaps in understanding the full 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?

Schema description coverage is 0%, so the description must explain the parameters. It does this directly: 'need' is described as 'what you need in plain language' and 'budget' as 'max spend'. This adds essential meaning beyond the bare type declarations in the schema, fully compensating for the lack of schema descriptions.

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

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

The description clearly states the tool performs 'TASK+BUDGET procurement' with a specific verb and resource. It distinguishes itself from sibling tools by focusing on executing a purchase/service engagement, unlike discovery or routing tools, with details like 'picks the best verified service' and 'executes with failover'.

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

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

The description provides clear usage context: 'describe what you need in plain language + max spend' tells the agent how to invoke the tool. However, it does not explicitly state when not to use this tool or mention alternatives, leaving the when-to-use versus siblings implied rather than explicit.

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. It discloses meaningful behaviors: failover if a service is down, no charge if nothing delivers, and dynamic pricing via '_meta'. However, it omits other relevant traits such as authentication requirements, rate limits, or whether the operation has side effects beyond paying and relaying data.

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

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

The description is three sentences long and every sentence adds value: the first explains the core mechanism, the second highlights the integration scope, and the third addresses pricing. It is information-dense without fluff, and the structure front-loads the most important action first.

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 must cover both behavior and return expectations. It explains the process well but does not mention what the response looks like or how failures are signaled beyond failover. Given the moderate complexity and the presence of sibling tools, some guidance on distinguishing use cases would improve completeness.

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

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

The input schema shows two bare string parameters with 0% description coverage, but the description compensates by explaining that the tool operates 'by url or capability,' indicating that these are alternative selection methods. This adds essential meaning beyond the schema, though it does not specify formats or precedence.

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: paying through Aegis to buy a verified service and relay data, with parameters 'url' or 'capability'. It identifies a specific resource and action, but it does not explicitly distinguish itself from the sibling 'route_batch', making its differentiation somewhat 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 phrase 'One integration reaches the whole registry' implies this is a primary access point, but no explicit guidance is given on when to use this tool versus alternatives like 'discover' or 'route_batch'. There are no stated exclusions or conditions for when not to use it, so the usage context 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 and discloses key behaviors: 'Pay ONCE', 'Charged only if all deliver', 'per-item failover', and 'Dynamic x402 via _meta'. This gives meaningful insight into payment semantics and failure handling, though it could still mention what happens on partial success in more explicit detail.

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

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

The description is a single dense sentence that packs a lot of information: payment, batch, item format, failover, conditional charge, and x402 mechanism. It is concise and front-loaded, but the heavy jargon ('Aegis', 'x402', 'via _meta') may reduce clarity for agents unfamiliar with the domain.

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 must explain the full invocation context, including return/response behavior. It explains input shape and payment conditions but never says what the agent should expect as a result, what happens upon partial failure, or how to interpret the response. This is a significant gap for a financial transaction tool.

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

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

Schema coverage is 0% and the schema only defines items as an array of empty objects, so the description's 'items=[{url|capability, params?}]' provides essential structure not available in the schema. It explains the shape of each item (url or capability, optional params) and thus compensates well for the lack of schema detail, though the notation is terse and could be more explicit.

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 'Aegis fulfills MANY verified services', indicating a batch fulfillment tool, but it does not explicitly state 'route' or 'batch routing' as the core action. It distinguishes from siblings by emphasizing 'MANY' vs. single, but lacks a clear verb+resource statement that would make the tool's purpose obvious on its own.

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 batch usage through 'MANY' and 'per-item failover', but never explicitly states when to use this tool instead of the sibling 'route' or others. There is no mention of alternatives, exclusions, or context like 'use for multiple items; use route for a single item.'

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. It usefully discloses the cost ($0.01 via x402) and the LLM intent-matching mechanism, but it does not explain the return format, what 'verified services' means, or any side effects or security considerations.

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 that immediately tells the user what to do, followed by the mapping mechanism and cost. Every word earns its place, with no redundancy.

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

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

The tool is simple (one parameter, no nested objects), and the description covers the basic input and pricing. However, there is no output schema and no description of what the tool returns, which is a notable gap for an agent selecting and invoking 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?

The schema has one query parameter with no description, and schema coverage is 0%. The description adds meaning by explaining that the user should 'describe what you need in plain language', which maps directly to the query parameter. However, it lacks examples, constraints, or details about accepted 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 maps plain-language requests to verified services via LLM intent matching, giving a specific verb and resource. It does not explicitly distinguish from the sibling tool 'discover', so it falls short of a 5.

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

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

The phrase 'Describe what you need in plain language' implies the primary use case, but there is no explicit guidance on when to use this tool versus siblings like discover, procure, or route. No exclusions or alternatives 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?

With no annotations at any level, this description carries the full load and discloses genuinely important behavior: calling the tool costs real money ('Aegis pays real money to confirm delivery') and passes an explicit $0.00 cost 'Paid $0.05 via x402' as well as the output spec. Timeout, failure, refund, and caching behavior isn't covered, but the cost-driven side effect is exactly the information an agent needed to be aware of.

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 front-loads the crucial claim and may be the same result sentence lists all return parts and the differentiator. Payment importance is matched twice ('Aegis pays real money' and 'Paid $0.05 via x402'), which works in a compact way; both meet expectations, and the whole text is short enough to be processed quickly.

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 no annotations, the description manages to spell out the provided output components (score, tier, recommendation, explainable confidence+reasons+evidence) and to state the mandatory $0.05 fee, which covers the major gaps. What it doesn't explain are complement and edge cases, e.g., what happens when a payment or verification fails — but for a small one-parameter tool at a nominal fee, the core is complete.

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

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

The schema has url as a plain string with no description (0% coverage), so the description had ample room to explain it, but the word 'url' doesn't appear in the description at all. The purpose 'Before you pay...', implies the URL is the destination to verify, so the context mostly fills in the gap, but no explicit semantics, normalization, or valid domains are given to fully compensate for the map's absence.

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 an active, identifiable resource: it returns a 'trust verdict' with score, tier, recommendation, and explainable confidence+reasons+evidence, based on a paid-delivery verification performed before the user pays. It also separates itself from coverage-only scores ('coverage-only scores cannot'), providing a clear purpose and a start on differentiation, though no sibling tool is explicitly named.

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 gives a clear point for when to use the tool: 'BEFORE you pay'. It implies that coverage-only scoring tools cannot deliver this kind of proof, but it does not name an alternate sibling to use when you only need coverage or reputation, so the usage boundary in the sibling family is implicit rather than prescriptive.

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