Research Agent by Nova (CIVAI)

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

With no annotations, the description carries the full behavioral burden. It usefully discloses the iterative/recursive nature, which signals long-running, potentially expensive execution and explains the duration and query caps in the schema, but it says nothing about permissions, the connection_id requirement, cost, or failure modes.

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-formed sentence that front-loads the core purpose and then explains the mechanism. Nothing is padded or redundant.

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 tool is complex (7 parameters, no output schema, no annotations) and the description leaves the return value entirely unspecified even though no output schema exists to cover it. The agent knows what the tool does procedurally but not what it yields or how results are shaped.

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%, and each parameter (depth, breadth, max_total_queries, max_duration_seconds, connection_id) is documented with ranges and defaults in the schema. The description adds no parameter-level meaning beyond what the schema already provides, 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 gives a specific verb (conduct) and resource (deep, iterative research) and even explains the mechanism: generating multiple queries, processing results, and recursing. It is clearly a research-execution tool, but it never contrasts itself with the sibling research__generate-research-report, so an agent must infer the boundary.

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 when-to-use guidance, no prerequisites, and no mention of the natural alternative, research__generate-research-report (report vs. raw research). The agent gets a description of the mechanism but no instruction on when this tool is the right choice.

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 behavioral burden. It does not say whether the generated report is persisted or merely returned, what format/length to expect, or whether it requires prior research artifacts — for a generative tool with zero annotation coverage this is a real 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 waste; 'comprehensive' is mildly decorative but the purpose is stated 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?

A simple two-parameter tool with fully documented params and no output schema, but the description never states what the tool returns or where the report goes, which is exactly the information missing when no output schema exists.

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%, so both parameters (objective, research_data) are already documented in the schema. The description adds no format, size, or structuring guidance beyond that baseline, so a 3 is appropriate.

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 (generate) and resource (research report) plus the input source (existing research data), so the agent knows this synthesizes rather than performs research. It does not explicitly distinguish itself from the sibling research__conduct-deep-research, which an agent might reasonably confuse it with.

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 is no when-to-use guidance, no prerequisite statement (e.g. that research must already exist), and no mention of the alternative research__conduct-deep-research for gathering new data. The agent must infer the routing decision entirely.

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 behavioral burden, and it delivers almost none. It does not say whether this tool performs any search, what the reply looks like, whether it has side effects, or how it behaves relative to search__search. The single sentence describes intent, not behavior.

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 sentence with no filler, and the trigger condition is front-loaded after the action. It is efficiently sized, though arguably so terse that it trades away necessary detail rather than earning conciseness through completeness.

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 tool is simple (one optional param, no output schema), so the bar is low, and the description covers the core intent. However, with no annotations and no output schema, an agent still lacks any signal about what calling this tool actually produces or when it should be chosen over search__search.

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% and there is one optional parameter (reply_hint) already documented in the schema. The description adds no additional meaning about reply_hint's content, format, or effect, 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 gives a clear verb+behavior ('Reply conversationally') and a triggering condition ('when the request is ambiguous or needs clarification'), so an agent can grasp what the tool is for. It does not name or contrast against its siblings (search__search, research__conduct-deep-research), so it stops short of full sibling differentiation.

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 states a clear trigger condition: use it when the request is ambiguous or needs clarification. That is genuine when-to-use context, but there are no explicit exclusions nor any mention of the alternative tools an agent should prefer when the request is not ambiguous.

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 behavioral burden, and it discloses only that the operation is live and that output is summarized. It says nothing about latency, rate limits, cost, result count, or failure behavior of an external Google call.

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 tight sentence with the action front-loaded and no wasted words. It is appropriately sized for a one-parameter tool, though it is arguably too terse to be maximally useful.

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 simple one-parameter tool with no output schema, the description at least signals that the return is a summary rather than raw links. But with no annotations and no parameter documentation, key details an agent needs to invoke it well are 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 coverage is 0% and the single 'query' parameter is typed only as a string with no description. The tool description says nothing about what form the query should take or whether modifiers/operators are supported, so it fails to compensate for the schema gap.

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 and resource ('Run live Google search') and adds that results are summarized, so the agent knows this retrieves fresh web results rather than canned data. It does not, however, differentiate from the sibling search__converse or the research__* tools, leaving the agent to infer which search surface to pick.

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 word 'live' hints that this is for current/real-time information, but there is no explicit when-to-use, when-not-to-use, or named alternative among search__converse and the research tools. The agent gets no routing guidance.

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