NessGate

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

With no annotations, the description carries the full safety burden and does so: it declares 'read-only' and 'client-agnostic' and specifies that results are 'read from the service's own metadata,' which explains why the assessment is authoritative. It does not cover failure modes, auth requirements for the underlying fetch, or rate limits, so it falls short of exhaustive disclosure.

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 tight sentences; the return shape and status vocabulary come first, and the routing hint to connect_domain comes last where it belongs. Every clause adds information, with no restatement of the tool name or title.

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, but the description compensates by enumerating the return contents (each connectable resource plus readiness status plus the exact missing field) and by flagging the operation as read-only. An agent has everything needed to call this correctly and interpret the result.

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?

Only one parameter and schema description coverage is 100% ('Registrable domain, e.g. example.com'), so the schema already documents the input fully. The description adds no format, normalization, or validation nuance about the domain beyond what the schema 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?

Specific verb+resource: 'Given a domain, return each connectable resource it publishes with a readiness assessment.' It also enumerates the four possible statuses (ready | credentials-required | incomplete | broken), which pins down the semantics, and names the sibling connect_domain so it is distinguishable without opening sibling schemas.

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 names the alternative explicitly ('Use connect_domain when you know the client's capabilities') and gives the discriminating condition, which by implication is also the when-to-use condition for this tool (you don't yet know capabilities). discover_domain is not mentioned, but no inference is needed to choose between this and connect_domain.

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 does so well: it declares read-only, states credentials stay with the caller and are never transmitted, notes matching is deterministic with no scores, and enumerates failure outcomes including under-published services. It does not mention rate limits, caching, or what an unknown/unregistered domain yields, so it falls short of a 5.

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 outcome list leads the sentence and the return shape, determinism, and safety guarantees follow in a compact block with no filler. It is dense and slightly overloaded for one sentence, but every clause carries 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 no annotations, the description must cover both return shape and safety, and it does list the plan contents (protocol, endpoint, transport, version, published auth metadata) plus the read-only/no-credential posture. It leaves open edge behavior such as unknown registrable domains, so it is strong but not fully 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 100% across both parameters, including the nested supports/auth/versions/transports and the clientAssumed default behavior, so the schema already does the heavy lifting. The description reinforces the role of client capabilities but adds no syntax or format detail beyond the schema, matching the baseline 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 gives a precise verb+resource ('return HOW the client can connect' for a given domain) and enumerates the exact outcome space (ready | credentials-required | incomplete | broken | no-compatible-method), which makes its scope unmistakable. It never names discover_domain or check_readiness, so the agent gets no explicit sibling routing, keeping this at a 4 rather than 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 preconditions are stated ('Given a domain AND the calling client's capabilities') and the purpose implies when it is useful, but there is no explicit when-to-use versus discover_domain or check_readiness, and no exclusion conditions. Usage is implied rather than directed.

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 does well: it discloses that NessGate reads the domain live, stores nothing, adds no ownership/safety claim, and that each returned resource carries a sourceUrl for verification. This is meaningful behavioral context, though it omits failure behavior (what happens when a domain publishes none of these) and any rate-limit or timeout information.

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-loaded with the core action and input, then the endpoint list, then trust/verification caveats. The long enumeration is informative rather than filler, though it is somewhat dense for three sentences.

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

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

With no output schema, the description usefully sketches the return contract ('one normalized answer', per-resource sourceUrl) and states the live/no-storage behavior. Missing only edge-case handling and any indication of result size or shape when discovery yields little.

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

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

Schema coverage is 100% and the single 'domain' parameter is fully documented in the schema, so the baseline is 3. The description adds only 'Given a domain', with no extra format or validation detail (e.g. subdomain handling) beyond the schema's registrable-domain clarification.

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 (read a domain's published machine-discovery resources) and enumerates the exact locations checked (llms.txt, /.well-known/ard.json, agent-card.json, api-catalog, openapi.json), leaving no ambiguity about what it does. An agent can immediately tell this resolves a domain's metadata rather than, say, fetching a URL or calling an API.

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 are no sibling tools, but the description only implies the trigger (resolve what a domain publishes) rather than stating when to reach for this versus other approaches. It never says when not to use it or what scenario makes it the right first step.

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