Google Docs Agent by Nova (CIVAI)

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

No annotations are provided, so the description must carry the full behavioral load. It says it replies conversationally, which implies a non-mutating response, but does not disclose side effects, authorization needs, response format, or whether it can access document context, leaving significant gaps.

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. It is appropriately sized for a simple fallback tool.

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 annotations or output schema, the description states when to use it but omits what the reply looks like, how reply_hint influences it, and any behavioral expectations. It is minimally adequate but incomplete.

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 parameter reply_hint is already described in the schema. The description adds no meaning beyond the schema, 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?

States a specific action ('Reply conversationally') and the triggering condition, so the agent understands it is a clarification/fallback tool rather than a doc CRUD tool. It does not name an alternative or further scope the resource, so it falls short of 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?

Explicitly gives the condition for use ('when the request is ambiguous or needs clarification'), which is clear usage context. No alternatives or when-not guidance are provided, so it is not a 5.

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 provided, the description carries the full disclosure burden and discloses nothing: no information on required auth/permissions, whether the created doc is empty, whether it is shared, what it returns, or any side effects. 'Run ... action: create doc' restates the name without behavioral content.

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?

It is a single short sentence, so it is not verbose, but the 'Run Google docs action:' prefix is filler rather than front-loaded useful information. Brevity here comes from under-specification rather than efficiency.

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 creation tool with no annotations, no output schema, and a vague generic 'detail' parameter, the description should explain at minimum what gets created and what the caller receives back. It leaves the agent unable to predict the result or the required input content.

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 exists and schema description coverage is 100%, so the schema already documents 'detail' as 'Task-specific details from the objective.' The description adds no additional meaning about what detail should contain for doc creation, 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 names a specific verb and resource ('create doc'), enough to separate it from delete_doc/get_doc/list_docs at a glance. However 'Run Google docs action:' is redundant wrapper text that adds nothing, and it never states what the doc initially contains or how it is named.

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 indication of when to use this tool versus docs__rewrite_doc, docs__get_doc, or the other siblings, nor any prerequisite or precondition. The agent is given no criteria for selecting 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?

No annotations are provided, so the description carries the full behavioral burden, yet it says nothing about destructiveness, irreversibility, required permissions, or whether the deleted doc is recoverable. For a delete operation this is a critical omission.

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?

Very short, but the boilerplate 'Run Google docs action:' prefix is filler that duplicates the namespace and dilutes the front-loaded intent. It is concise without being substantive.

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 destructive, annotation-free tool with no output schema needs to explain irreversibility and any confirmation requirements; none of that is present. An agent cannot safely decide to invoke this based on the description alone.

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 ('detail') and schema description coverage is 100%, so per the calibration baseline the schema already documents it. The description adds no meaning about what detail should contain for a delete action, so it neither helps nor harms.

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 ('delete doc'), which is enough to distinguish it from siblings like docs__get_doc, docs__create_doc and docs__rewrite_doc. The generic 'Run Google docs action:' prefix adds no value but doesn't obscure the purpose.

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 alternatives. The only hint of usage is the tool name itself; nothing tells the agent when deletion is appropriate versus rewriting or leaving a doc alone.

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 of behavioral disclosure, yet it says nothing about return format, whether it requires an ID, permission requirements, or error behavior. It only weakly implies a read operation via 'get'.

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?

It is a single short sentence with no padding, but the generic 'Run Google docs action:' prefix is low-value filler rather than a meaningful front-loaded statement of the operation.

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 retrieval tool with no output schema and no annotations, the definition should explain what is returned and whether an identifier is needed. None of that is present, leaving significant gaps an agent cannot resolve from the other fields.

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 the single 'detail' parameter is documented in the schema itself, giving the baseline of 3. The description adds no interpretation of what 'detail' should contain, but the schema-coverage rule caps the concern here.

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 phrase 'get doc' names a verb and resource, so the basic operation is inferable, but it is wrapped in generic boilerplate ('Run Google docs action:') that adds nothing and the definition reads as a near-restatement of the tool name. It gives no signal to distinguish it from siblings like docs__list_docs or docs__converse.

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 indication of when to use this tool rather than docs__list_docs for enumeration or docs__converse for content work. No prerequisites, exclusions, or alternative selection logic are provided.

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 burden. It does not state that this is a read-only operation, whether results are paginated, how many docs are returned, or what auth is required. 'List' weakly implies non-mutation but nothing is disclosed.

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 short sentence with no wasted clauses, but it is boilerplate rather than deliberately concise — the brevity comes from under-specification, not from economical expression.

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 list tool with no annotations and no output schema, the description should at least describe the returned collection or pagination behavior. Neither is present, leaving real gaps an agent would need to resolve.

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 there is only one parameter ('detail'), whose own schema description ('Task-specific details from the objective') is opaque. The tool description adds no meaning beyond the schema, so the baseline 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 names a verb (list) and resource (docs) inside a generic 'Run Google docs action:' wrapper, so the purpose is inferable. It does not distinguish itself from the sibling get_doc or explain what 'list' returns, so the differentiation is only implied.

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 indication of when to choose this tool over docs__get_doc, docs__converse, or the research tools. The agent must guess from names alone.

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 nothing. It does imply mutation/overwrite of an existing document (useful), but says nothing about whether the original content is lost, whether permissions are required, whether it is reversible, or how the new content is determined.

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?

It is a single short, front-loaded sentence with no padding, which is fine structurally. However, it reads as generic auto-generated boilerplate ('Run <product> action: <verb> <resource>') that spends its one sentence restating the tool name rather than conveying 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?

For a mutating tool with no annotations and no output schema, the description omits everything an agent needs: how the rewrite is produced, what input content is expected, what happens to the existing document, and what a successful call returns. The gaps are significant relative to the tool's complexity.

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% for the single 'detail' parameter, so the schema already documents it; per the baseline rule a 3 is appropriate. The description adds no additional meaning about what 'detail' should contain for a rewrite operation.

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 verb ('rewrite') and a resource ('doc'), and the sibling list (create/delete/get/list_doc) makes the general category clear. But it does not say what a 'rewrite' actually does — full-content replacement, targeted edit, or LLM-driven rephrasing — so the agent cannot distinguish its precise effect from create_doc or a hypothetical update tool.

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 statement of when to use this tool versus alternatives such as docs__create_doc or docs__get_doc, nor any prerequisite (e.g., must the doc already exist, must an ID be supplied). Usage must be inferred entirely from the tool name.

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 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.