Agent Preflight

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

Annotations already establish this as a read-only, non-destructive operation, and the description adds context about the tool's cost ($0.05 USDC) and the HTTP method (GET). It does not contradict the annotations and provides additional behavioral detail about the check's scope (access, login, CAPTCHA).

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 followed by an example, front-loading the key purpose 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?

For a simple single-parameter check tool with good annotations, the description covers the core purpose, cost, and invocation example. It does not explain response format, but the absence of an output schema and the tool's simplicity make this acceptable.

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, `url`, is documented in the schema with a URI format, but the description's example is the sole mention and adds no new semantics. With 0% schema description coverage, the description fails to compensate by explaining parameter constraints or behavior, making this a weak area.

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

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

The description explicitly states 'URL access, login, and CAPTCHA check' with a concrete example, clearly identifying the tool's function. It distinguishes itself from sibling tools like preflight and premium_preflight by focusing on access and login verification.

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

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

The description provides a clear example of how to invoke the tool (GET /v1/access-check?url=...), implying usage for checking URL accessibility. However, it does not explicitly compare with sibling tools or state when not to use it, so it lacks explicit exclusions.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds the cost ($0.10 USDC) and an example HTTP GET pattern, which are useful, but it does not disclose output format, error behavior, authentication needs, or rate limits. 'Signals' gives a vague hint of return content.

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

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

The description is two concise sentences: the main purpose is front-loaded, followed by cost and an example. Every word adds value, with no filler or repetition.

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 discovery tool with no output schema, the description covers purpose and invocation (via example) but lacks details on return structure, edge cases, or usage context relative to similar tools. It is adequate but not comprehensive.

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 required 'url' parameter with 0% description coverage. The example '?url=https://example.com' partially demonstrates the parameter's meaning, but the description does not explicitly state that the URL is the target to scan. It compensates somewhat but leaves room for ambiguity.

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: 'Discover OpenAPI, Swagger, GraphQL, MCP, and API documentation signals.' It uses a specific verb and resource list, and the name 'api_discovery' matches. The focus on discovery distinguishes it from sibling preflight/check 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 implies usage through the example 'GET /v1/api-discovery?url=https://example.com' but does not explicitly state when to use this tool vs alternatives like access_check or preflight. There is no mention of alternatives or exclusions, so guidance is only implicit.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description only needs to add beyond that. It discloses the paid-request behavior and the $0.35 USDC cost, and indicates it is 'standard' preflight (vs premium). However, it does not describe response format, error behavior, or what a successful batch outcome looks like, leaving some behavioral 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 two sentences: one stating the action and scope, the other providing price and an example endpoint. It is tightly written with no filler, front-loading the core 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?

The tool has a single parameter and helpful annotations, but no output schema. The description covers what it does, cost, and an example, yet omits what the response looks like and how failures are handled. It is adequate for a simple tool but leaves some contextual 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 only parameter 'urls' is semantically explained as the URLs against which preflight runs, and the 'up to 10' limit matches the schema's maxItems. The description provides some compensation for the 0% schema coverage, but it largely repeats the schema and does not add deeper details like URL format expectations or behavior for invalid URLs.

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 action ('Run standard preflight'), its scope ('against as many as 10 URLs'), and its paid nature, distinguishing it from a single-URL preflight tool. The verb and resource are specific, leaving no ambiguity about what the tool does.

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 when to use this tool (when you need to preflight multiple URLs in one request) and provides the cost context. However, it does not explicitly name alternatives like 'preflight' or 'premium_preflight', and does not state when not to use it, so it lacks explicit exclusions.

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

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

Annotations already indicate non-read-only and open-world behavior, so the description's burden is lower. It adds useful context like the $0.10 cost and the comparison mechanism, but does not disclose whether it writes to KV or rate limits. This is acceptable given annotation coverage, but not richer.

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 core behavior, followed by cost and an example. Each sentence carries value, though the example endpoint is slightly redundant with the tool name.

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 tool with no output schema, the description explains the core operation and pricing but omits what the response looks like (e.g., changed/unchanged) and the meaning of 'prior KV observation.' It is adequate but not fully self-contained.

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 'url' parameter with 0% description coverage. The description only mentions 'URL' without adding meaning beyond the schema, failing to explain accepted formats, edge cases, or how the URL is used in fingerprinting. It does not compensate for the coverage gap.

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 fetches a URL and compares its content fingerprint with a prior KV observation, naming the specific action and resource. It distinguishes from siblings by focusing on change detection, though it does not explicitly contrast with other check 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?

No guidance is provided on when to use this tool versus alternatives like preflight or access_check. The description includes price and an example endpoint but lacks conditions, exclusions, or mention of sibling tools.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds meaningful context: a cost of $0.15 USDC, a single-fetch behavior, and the nature of the returned data (access checks, commerce signals, risk). It does not contradict annotations, but it does not disclose other behavioral details like rate limits or error handling, though the bar is lower given the annotations.

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

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

The description is concise at two sentences plus an example, and it front-loads the core purpose. The price and example add useful context without bloat. However, the example's inclusion of 'intent' could be considered unnecessary or misleading, slightly degrading the structure.

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

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

For a simple tool with one parameter and no output schema, the description covers core functionality, price, and a usage example. It is reasonably complete but lacks any mention of what the response structure looks like (though no output schema exists) and does not address the relationship to sibling tools. The misleading 'intent' parameter in the example further reduces completeness.

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

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

Schema description coverage is 0%, and the description does not adequately compensate. The only parameter 'url' is not explicitly explained, though the format 'uri' provides some clarity. The example uses 'intent=research' which is not in the schema, creating confusion about accepted parameters. This is a significant gap for a tool with a single parameter.

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 that the tool provides 'Single-fetch URL intelligence, access checks, commerce signals, and risk,' which clearly indicates its function. The term 'single-fetch' differentiates it from sibling batch_preflight, and the listed features distinguish it from narrower tools like access_check. However, it lacks an explicit verb such as 'fetches' or 'analyzes,' so it falls short of a fully specific 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 guidance is given for when to use this tool versus alternatives. The phrase 'single-fetch' implies it is for one URL at a time, but it does not mention batch_preflight for multiple URLs or premium_preflight for advanced features. The example includes an 'intent' parameter not present in the schema, which may mislead rather than clarify 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?

Annotations provide readOnlyHint=true and destructiveHint=false, which the description does not contradict. The description adds useful behavioral context: retries, redirect evidence up to five hops, access controls, commerce risk, can_proceed, and proof. This goes beyond the minimal annotations and gives the agent a better sense of what the tool does internally, though it could be more explicit about retry conditions and output format.

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, compact and to the point. It packs many features into a short space without excessive fluff. However, the list-like structure makes it less readable and prioritizes marketing terms over functional clarity, so it loses a point for structure.

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

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

Without an output schema, the description must explain what the tool returns and how to interpret results, but it only mentions 'can_proceed' and 'proof' without elaboration. It also omits a clear statement of the tool's overall purpose and any context about when to rely on its output. For a complex tool like this, the description is 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?

Schema coverage is 0%, but the single required parameter 'url' is illustrated in the example. The description does not explain the parameter's meaning or constraints beyond the example, but the URI format and the tool's purpose make it inferable. This is borderline; an explicit statement like 'the URL to preflight' would improve it.

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 lists features ('Triple-user-agent intelligence', 'five-hop redirect evidence', 'commerce risk') but never states a clear action or outcome. It does not explicitly say 'checks a URL' or 'performs a risk assessment'—it relies on the tool name and example to imply purpose, which is insufficient for selecting among siblings like preflight or batch_preflight.

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 instead of alternatives. It does not mention scenarios, prerequisites, or exclusions. The name 'premium' implies it is a more advanced version of preflight, but the description never states that or compares it to batch_preflight or other 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 already disclose readOnlyHint=true, openWorldHint=true, and destructiveHint=false, covering safety and external access. The description adds the monetary cost ('Price: $0.15 USDC') and an example endpoint, which are valuable behavioral details. No contradictions detected.

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, consisting of two sentences. It is front-loaded with the primary purpose, followed by cost and an example. Every sentence adds necessary information without waste.

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 one parameter and strong annotations, the description covers purpose, cost, and an example sufficiently. It does not explicitly describe the output format, but the named extracted signals ('price, availability, add-to-cart, and commerce risk signals') imply the return content. Minor gaps include failure behavior or response structure, but overall it's 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?

The schema only defines a 'url' with format 'uri' and no description. The description compensates slightly by showing an example query string ('?url=https://example.com'), which clarifies the parameter usage. However, it does not explain accepted URL types, encoding, or other constraints, so it only partially compensates for the 0% schema description 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 states a specific verb+resource: 'Extract product price, availability, add-to-cart, and commerce risk signals.' It clearly identifies what the tool does and distinguishes it from sibling preflight/discovery tools by focusing on product intelligence. The example endpoint reinforces the purpose.

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?

Usage is implied: an agent would use this when needing product price, availability, or commerce risk signals from a URL. However, there is no explicit mention of when to use this over alternatives, nor any exclusions. The example provides a basic usage pattern but not contextual guidance.

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