AgentWorkmark

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world behavior, so the safety profile is covered. The description adds value beyond that by disclosing what the result contains (observed time and expiry) and explicitly ruling out side effects ('does not reserve capacity or initiate work'), which is exactly the kind of context annotations cannot express.

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?

Three short sentences, zero filler, with the core check front-loaded and the exclusions following. Every sentence 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 tool with no output schema, the description is nearly complete: it covers the purpose, the exclusions, and what the response conceptually includes. The only gap is any hint about failure modes when a service is not accepting work, which is minor.

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% for the single serviceId parameter, so the description carries the burden and it does not explain the parameter at all. The name 'serviceId' with uuid format is largely self-explanatory against the tool's stated resource, keeping this at an adequate-but-unexplained baseline rather than a failure.

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 ('check whether a service is reviewed and currently accepting work') and clarifies the return content. It implicitly distinguishes itself from search_available_services by operating on a single serviceId, but it never names the sibling alternatives, so the differentiation is left to inference.

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 clause 'Does not reserve capacity or initiate work' usefully sets a negative boundary, telling the agent this is a pure check. However, it gives no positive routing guidance (when to prefer this over search_available_services or get_service_evidence), so usage 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?

Annotations already declare readOnlyHint, idempotentHint, safe reads. The description adds genuinely new behavioral context: that provider-authored content is reported as data, separated from reviewer findings — useful for interpretation. But it doesn't disclose output shape, pagination, or what 'public evidence' entails beyond that.

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?

One tight sentence pair with no filler; the scope and the provider-vs-reviewer distinction are front-loaded and immediately actionable.

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 inspection tool with a single param, the description covers what is returned at a high level and flags the authorship distinction. It still leaves the caller unsure about output format, size, and where serviceId comes from, which matters since there is no output schema.

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 single param serviceId has only a uuid format with no description. The description doesn't clarify serviceId's origin or meaning, only implying it identifies 'one currently available service'. With one parameter, baseline behavior is modest but an explanation of where serviceId comes from would have helped.

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 resource (evidence, review findings, limitations for a service), and adds a distinguishing detail that provider-authored context is separated from reviewer findings. Doesn't explicitly contrast with siblings check_availability and search_available_services, but the purpose is concrete and distinct.

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 'for one currently available service' implies a precondition (the service must be available), which hints at usage after search/availability checks. However, it never explicitly says when to use this versus the sibling tools or states prerequisites like needing a previously obtained serviceId.

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, closed-world. The description adds value beyond them by enumerating what the response contains (service scope, evidence, limitations, availability timestamps) and explicitly ruling out side effects like contacting providers or placing orders.

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?

Three short sentences, front-loaded with the core action, then return contents, then exclusions. Every sentence earns its place with no padding.

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?

No output schema exists, but the description compensates by summarizing returned fields, and annotations cover the safety profile. The remaining gap is parameter semantics: with 0% schema coverage, the description should explain query/category behavior to be 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 0% with two parameters (query, category). The description says nothing about what query matches against or what the category enum values mean, so an agent must infer parameter usage entirely from the bare 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?

Clear specific verb+resource: 'Search independently reviewed AI services currently accepting work.' It conveys scope ('independently reviewed', 'currently accepting work') beyond the title, though it does not name or differentiate from siblings check_availability or get_service_evidence.

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 negative scope ('Does not contact providers, place orders, or execute jobs') implies when this tool is appropriate versus action tools, but there is no explicit guidance on when to use it instead of check_availability or get_service_evidence. Usage is implied rather than stated.

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