Prooftask

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds a behavioral fact the annotations do not carry: no credential is required, which matters for an agent deciding whether it can call this before authenticating. It does not describe the shape or size of the capability payload, a minor remaining 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?

A single front-loaded sentence with no filler; the credential constraint is placed at the end where it reads as a qualifying condition rather than burying the action.

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, annotation-documented read tool, the description covers what is read and the auth condition. With no output schema, a brief note on what the returned capabilities contain would have closed the last gap, but nothing required to call 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 takes zero parameters and the schema is fully described, so there is nothing for the description to compensate for. Baseline of 4 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?

States a specific verb ('Read') and enumerates the exact resource scope (connection, billing, client capabilities). This is plainly distinct from the sibling tools, which deal with public specifications rather than agent capabilities, so an agent can route correctly without opening a 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?

'Without a credential' implies the calling context (unauthenticated access) but the description never states when to prefer this over getPublicSpecification or searchPublicSpecifications. Usage is inferable from the resource name rather than explicitly guided.

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 readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description still adds non-redundant behavioral context: 'No credential needed' (auth requirement) and the domain-specific non-effects that this call 'creates no draft, agreement or acceptance and never grants authority' — information not derivable from the hints alone.

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?

Four tight sentences, front-loaded with the core read action and progressively adding provenance, auth, workflow and effect semantics. Nothing is padded, though the workflow-review sentence is a touch beyond the minimal call contract.

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 read-only tool with no output schema and fully undocumented nested params, the description does good work: it identifies the returned artifact and names the substantive fields to review (scope, completion criteria, required evidence), implying payload content. It stops short of describing pagination, versioning behavior, or error cases, but nothing essential to invoking 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?

Schema description coverage is 0%, so the schema documents only types, patterns and bounds for the nested 'path.id' and 'query.version' objects. The description partially compensates by indicating the values come from the searchPublicSpecifications result, but it never explains the id format or version semantics, leaving the meaning of both parameters largely inferred.

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 and resource ('Read the exact public template version') and ties it precisely to the identifier produced by searchPublicSpecifications, which cleanly separates it from that sibling and from getAgentCapabilities. An agent knows exactly what object this returns without opening the 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 opening sentence establishes the required workflow (call searchPublicSpecifications first, then read the returned version) and the later sentence prescribes reviewing scope, completion criteria and evidence with the user before recommending adoption. It gives clear context for use but never states an explicit when-not-to-use or names a true alternative tool.

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 readOnly/idempotent/openWorld/no-destruct, so the safety bar is covered. The description adds genuine value beyond that: no auth requirement, empty-results semantics with an explicit anti-hallucination instruction, a caveat that results are not quality certification or payment proof, and a version/digest pinning step before reuse. Return format and pagination remain unstated.

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?

Purpose is front-loaded in the first clause, and each following sentence carries a distinct constraint (auth, empty results, data caveats, version pinning). The caveat sentence is the longest and slightly dense, but nothing is 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?

For a search tool with no output schema and zero schema-level parameter docs, the description covers the important agent questions: credentials, empty results, trust level of results, and reuse safety. The notable remaining gap is what the returned items actually contain and whether results are paginated.

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 single parameter is a nested object with q and industry fields. The description compensates partially by giving example query values ('automation, customer support or software') that map to q, but the industry field and the q/industry split are never explained.

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 and resource: 'Find public delivery acceptance templates'. The search-by-scenario framing implicitly separates it from the getPublicSpecification sibling, which fetches by identity, but the description never names that alternative. Clear but not explicitly differentiated from siblings.

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?

Gives real context for when to call it ('before asking a user to connect') and a precondition ('No credential needed'), plus handling for the empty-result case. It stops short of naming getPublicSpecification as the follow-up tool once a template is chosen, so the routing is only implied.

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