ApyHub Utility Tools (US)

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered externally. The description adds little behavioral context beyond 'invoke' and the flat-args requirement; it does not reveal side effects, error behavior, or irreversible consequences, but it does not contradict 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?

Two efficient sentences front-load the main action and immediately explain parameter semantics. Every clause 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?

Given the destructiveHint and openWorldHint, the description could usefully warn that invoking an endpoint may perform mutating or side-effectful actions, and it says nothing about expected return values or error behavior. However, it is complete enough for an agent that has already consulted the spec via the named discovery tools.

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 description carries the full burden for parameters. It explains the provenance of 'service' and 'endpoint' as unikeys from catalog discovery tools and defines 'args' as a single flat object matching the target endpoint's input schema—essential meaning that the bare schema lacks.

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: 'Invoke a catalog endpoint.' It also distinguishes itself from sibling discovery tools ('search_apis', 'get_api_spec') by explaining that 'service' and 'endpoint' are unikeys sourced from those tools, making it the execution counterpart to discovery.

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 actionable guidance: obtain unikeys from 'search_apis/get_api_spec' before calling, and provide 'args' matching the endpoint's input schema. This conveys the intended workflow relative to the sibling tools, though it doesn't explicitly state when not to use call_api.

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 openWorldHint=true, covering the safety profile. The description adds that it returns endpoint summaries and that it should be called first, which is behavioral guidance beyond annotations. No contradictions with the read-only nature.

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 concise sentences with zero waste. The first states the purpose, and the second gives the usage order relative to search_apis. Information is front-loaded and 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 zero-parameter listing tool with read-only annotations, the description fully covers what it does, when to use it, and how it relates to sibling tools. 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, so the schema is fully covered by default. The description does not need to add parameter semantics, and the baseline of 4 is appropriate since no additional context is required.

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 lists curated API endpoints with summaries, using a specific verb ('List') and resource ('API endpoints'). It also distinguishes itself from search_apis by the 'Always call this FIRST' instruction, making its purpose distinct and unambiguous.

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?

Explicitly instructs to call this tool before search_apis and to use curated endpoints directly if available, skipping search. This provides clear when-to-use and when-not-to-use guidance, naming the alternative tool and the condition for choosing it.

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 the behavioral context that this is a prerequisite lookup step and that it returns the complete spec needed for call_api. It doesn't describe pagination or error behavior, but for a read-only spec-fetch tool the annotations carry the main burden.

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, no filler. The core purpose is front-loaded, and the usage directive is placed at the end where it reinforces the workflow.

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 2-parameter read-only lookup tool with no output schema, the description covers the purpose, the source, and the workflow position. It could mention what happens if the endpoint isn't found, but the explicit 'always call this before call_api' directive makes the tool's role complete enough for an agent.

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 provides only names and types. The description says the tool returns the spec for 'one endpoint' and implies service and endpoint identify it, but it doesn't explain the expected format of the endpoint value (e.g., path string, ID). Baseline 3 is fair because the description adds some context but doesn't fully compensate for the 0% 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?

States a specific verb ('Get'), a specific resource ('full specification for one endpoint'), and the source ('from search_apis results'). It clearly distinguishes itself from siblings by naming the prerequisite search_apis and the downstream call_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?

Explicitly instructs when to use it: 'Always call this before call_api unless you already have the spec.' This is a clear directive that also names the alternative (call_api) and the condition that bypasses this 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?

The description reveals that results are candidate endpoints with summaries and a `scoped_to_curated` boolean, and explains how to interpret zero results when the boolean is true. This adds concrete open-world semantics on top of the openWorldHint annotation. There is no contradiction with readOnly or destructive hints.

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 sentences, all high signal and front-loaded: scope, usage condition, return summary, and next action. No filler or redundancy. It is as compact as the content allows.

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 workflow is complete: when to call, what it returns, how to interpret open-world zero results, and what to do next. With no output schema, the return description is sufficient for an agent to decide whether to proceed. The only meaningful gap is the undocumented `limit` parameter, which is a minor omission.

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?

With 0% schema description coverage, the description must compensate; it does for `query` by noting capability/name search and giving an example. However, the optional `limit` parameter is not described at all, so the agent is left to infer whether it caps result count or controls pagination. This is a partial compensation, not a full one.

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 action and scope: 'Search the full ApyHub API catalog by capability or name', with a concrete example. It also differentiates itself from curated_apis by saying to use it only after that sibling fails. This gives the agent a clear sense of the tool's role.

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?

Explicitly says 'Only use this if curated_apis didn't have what you need,' which sets the condition for choosing it over the sibling. It also tells the agent to follow up with get_api_spec before invoking the endpoint. No alternative is missing.

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