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

No annotations are present, so the description carries the behavioral burden. It does disclose the sequence of operations (DNS, TCP, HTTP(S)), but omits whether the tool is read-only, how failures or timeouts are handled, and whether any state changes occur. This is partial but not complete 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, front-loaded sentence with a colon followed by a compact, ordered list of checks. Every word earns its place; no redundancy or fluff.

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 an output schema and annotations, the description gives a clear high-level behavior but does not cover return format, error behavior, or how this tool relates to sibling diagnostics. For a low-complexity tool with a fully documented parameter schema, this is a moderate gap.

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

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

Schema description coverage is 100%: host, path, and port are each described with types and defaults. The tool description adds no parameter-specific meaning beyond what the schema already states, so the baseline of 3 applies.

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

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

The description clearly states a specific verb and resource: 'Full reachability diagnosis for any host', followed by a concrete sequence of checks (DNS, TCP, HTTP(S)). This distinguishes it from sibling tools focused on specific services like GitHub or proxy status.

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 provides clear context: use this when you need a comprehensive reachability diagnosis of any host. However, it does not explicitly reference sibling tools or state when not to use it, so it lacks exclusions and explicit alternatives.

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

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

No annotations are provided, so the description carries the burden. It does disclose the meaningful behavior: four named third-party resolvers are contacted, which implies external network egress and no local state change, and it frames the result as a comparison that surfaces disagreement. It says nothing about latency, timeout/failure semantics when one resolver is unreachable, or what the comparison output looks like, which matters for a tool with no output schema.

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, zero filler, and the operational summary is front-loaded before the explanatory rationale. Every clause 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 one-parameter read-only lookup with no output schema, the description covers what it queries, against whom, and why. The remaining gap is what the comparison actually returns (per-server answers? agreement flag? errors per resolver?), which would let the agent use the result without guessing.

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

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

Schema coverage is 100% for the single required 'host' parameter, so the schema already documents it. The description reinforces that the same question (hostname) is asked of every resolver, but adds no format or edge-case detail beyond that.

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 verb+resource: query the same name against AliDNS, DNSPod, Cloudflare and Google and compare the answers. That is clearly distinct from the sibling tools (proxy status, hosts check, registry check), though it never explicitly names a sibling as the alternative for a general 'network is broken' investigation. The purpose is unambiguous on its own terms.

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 second sentence supplies a concrete trigger condition — 'a host resolves but does not work' — which tells the agent exactly when this tool is the right call versus generic diagnostics. It stops short of stating exclusions or naming the sibling tools to use instead for other failure modes, so it is clear context without 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, so the description carries the full burden of behavioral disclosure. It discloses what the tool does (runs a comprehensive diagnostic across five categories) and what it produces ('report each finding with concrete suggestions about what to change'). The diagnostic/preflight framing strongly implies a read-only, non-mutating operation. It does not state permission requirements or response format, but for a zero-parameter diagnostic tool the disclosed scope and output behavior are solid.

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 with zero waste. The first sentence front-loads the full scope and output behavior; the second delivers the usage guidance. Every word earns its place and nothing is redundant with the schema, which is empty. This is model concision.

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 zero-parameter diagnostic with no output schema, the description covers the essential ground: the full check scope, the reporting behavior with suggestions, and the timing of use. An agent can decide to call it and know what to expect. It could marginally improve by routing to specific siblings for targeted checks, but nothing an agent needs to invoke it correctly is missing.

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

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

The tool has zero parameters and an empty schema, so per the rubric the baseline is 4. There is nothing for the description to add beyond what the schema provides, and it correctly requires no parameter explanation. This is the appropriate ceiling for a parameterless 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 uses a specific verb ('Run') and a clearly scoped resource ('the full network preflight'), then enumerates the five check categories (system proxy, proxy ports, TUN adapters, GitHub reachability, hosts conflicts). The 'full' designation plus the enumerated scope clearly distinguishes it from the targeted sibling tools like net_proxy_status and net_hosts_check, which each cover only one slice. An agent can tell exactly what this does and how it differs from its siblings 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?

The description gives an explicit usage directive: 'Use this before blaming the network for a failure.' This tells the agent when to invoke it as the first diagnostic step. It stops short of naming alternatives or explicit when-not-to-use conditions, but the 'full preflight' framing plus the enumerated sibling tools makes the intended decision point reasonably 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 provided, the description carries the full burden of disclosure. It clearly lists the three network checks performed and includes round-trip time, which is a helpful behavior detail. It does not mention failure modes, timeouts, or side effects, but for a read-only reachability probe the disclosed behavior is adequate.

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, well-structured sentence front-loads the primary purpose and appends the specific checks. Every word adds value; there is no fluff 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 zero-parameter, read-only network probe, the description provides all essential information an agent needs to decide whether to call it. The lack of an output schema is not a critical gap here because the tool's behavior is fully implied by the described checks, though a note on the response format would make it marginally more 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 correctly focuses on the tool's behavior rather than inventing parameter details. The empty schema needs no further explanation.

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 names a specific verb ('Check'), a specific resource ('github.com'), and the exact scope ('DNS resolution, TCP 443, and the HTTPS status code with round-trip time'). It is immediately distinguishable from sibling tools, which target proxy/diagnostic/network checks rather than a single host.

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

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

The description gives clear context: use this when you need to know whether github.com is reachable right now. It does not explicitly name alternatives or exclusions, but the specificity of the target (github.com) makes the intended use unambiguous even without referencing 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?

With no annotations, the description carries the full transparency burden. The verbs 'scan' and 'lists' clearly imply a read-only, non-destructive operation, and the explanation about proxy bypass adds behavioral insight. It doesn't explicitly state 'does not modify the file,' but that is strongly implied.

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 with no filler. The action is front-loaded, followed by the reason the tool exists. Every clause 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 zero-parameter, read-only tool with no output schema, the description explains the purpose, the behavior, and the result ('this lists what is pinned'). It could mention edge cases like missing file permissions, but overall it gives enough for an agent 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?

The tool has zero parameters, so there is nothing to clarify. The baseline of 4 applies because the description correctly omits parameter details that don't exist.

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 names a specific action ('Scan'), a concrete resource ('the Windows hosts file'), and a clear scope ('GitHub-related entries'). This cleanly separates it from the siblings, which deal with GitHub status and proxy state rather than host file pinning.

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 context for when the tool is relevant — pinned entries bypass the proxy and can go stale — so an agent understands why to run it. However, it doesn't explicitly name alternatives or state when not to use it, stopping short of the strongest 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 carries the full burden of behavioral disclosure. It mentions default ports and override behavior, but that is already in the schema, and it does not disclose side effects, permissions, or what the output of the probe looks like.

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, efficiently structured sentence that front-loads the core purpose before providing the default behavior. Every word earns its place, and there is no unnecessary detail.

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

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

The description explains what the tool does and its defaults, but omits the return value or output semantics, which matters given there is no output schema. It also does not clarify the relationship to the closely named sibling `net_proxy_status`, leaving the agent to infer competition.

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, `ports`, is fully described in the schema with a default list, giving 100% schema coverage. The description adds the nuance that passing `ports` overrides the defaults, but this is minimal added 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 states a clear verb (probe), resource (local proxy ports), and purpose (TCP reachability), making the tool's function distinct. It does not explicitly contrast with sibling tools like net_proxy_status, but the mention of local ports and defaults narrows its 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?

No guidance is given on when to use this tool versus alternatives like net_proxy_status or net_diag. The description implies usage for checking local proxy port reachability but does not state when not to use it or provide any selection 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?

With no annotations, the description must carry behavioral disclosure. 'Show' implies a read-only inspection and the second sentence usefully clarifies that there is no system-wide proxy switch on Linux or macOS, but it does not explicitly state side effects, permissions, or output shape.

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 with no wasted language. The core behavior is front-loaded and the environmental caveat follows immediately.

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 zero-parameter, read-only status tool with no output schema, the description identifies the exact configuration sources and explains why environment variables are authoritative on Linux and macOS. It does not describe the return format, but the tool's simplicity and source specification make the definition largely complete.

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

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

The tool takes zero parameters, so there are no parameter semantics to explain. The schema is empty and the description does not need to compensate for undocumented inputs.

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, 'Show', and a specific resource, 'proxy configuration', and scopes it to HTTP_PROXY / HTTPS_PROXY / ALL_PROXY / NO_PROXY. It is clear what the tool does, though it does not explicitly differentiate itself from the sibling net_proxy_probe.

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

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

The description explains the source of the proxy configuration but gives no explicit guidance on when to use this tool versus alternatives such as net_proxy_probe. It notes the Linux/macOS environment-variable constraint, but that is contextual scope rather than usage routing.

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 carry the whole burden; it does disclose the config resolution order and that both TCP reachability and HTTP status are exercised, which tells the agent this performs live network I/O rather than a local read. It stops short of stating side-effect freedom, timeouts, or how failures versus unreachable hosts are reported.

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, with the target resource and resolution order front-loaded and the triage hint last. Minor friction from the dense parenthetical and the repeated word in "npm registry npm is actually configured to use," but nothing 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?

For a zero-argument network diagnostic with no annotations and no output schema, the description covers what is inspected, how the registry is resolved, and when to reach for it. It leaves the shape of the result (per-endpoint statuses, how the two registries are compared) undescribed, which is the main remaining gap.

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

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

The tool takes zero parameters, so there is no parameter semantics to explain and the baseline is 4. The description correctly implies no arguments are needed, since everything is derived from environment and config files.

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?

Names a specific verb (check) and a precise resource: the npm registry actually in effect, resolved in a stated precedence order (environment → ~/.npmrc → official default), plus TCP and HTTP probing of both. This is clearly distinct from the sibling diagnostics (net_proxy_status, net_github_status, net_dns_compare), which cover other layers.

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 closing line "npm install failed usually starts here, not at GitHub" gives a concrete trigger condition and explicitly steers the agent away from the GitHub-oriented sibling. It does not say when the proxy, DNS, or doctor siblings would be the better first call, so routing among the rest of the family is left implicit.

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