Hive Consult

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

The description adds useful output behavior ('structured findings with confidence scores'), which is beyond the schema. However, annotations indicate readOnlyHint=false and idempotentHint=false, and the description does not clarify whether any side effects occur. It neither contradicts annotations nor fully explains behavioral implications.

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?

The description is concise, front-loaded, and contains no filler. It communicates the core purpose and output in two short sentences, making it easy for an agent to parse quickly.

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 has three parameters, all schematically described, and no output schema. The description adequately covers purpose, analysis types, and high-level output. It could detail the return structure further, but for a straightforward analysis tool it is reasonably 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 100%, so the baseline is 3. The description's mention of analysis types aligns with the 'analysis_type' enum, but it does not add meaning beyond what the schema already provides. The 'did' and 'data' parameters are also not further 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?

The description uses a specific verb ('Analyze') and resource ('data'), and clearly enumerates the analysis types: trends, anomalies, forecasts, or comparisons. It also mentions the return type (structured findings), distinguishing it from sibling tools like 'decide' and 'reason'.

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 provides clear context for when to use the tool by listing the supported analysis types (e.g., trends, anomalies, forecasts, comparisons). It does not explicitly mention alternatives or exclusions, but the use cases are sufficiently clear to guide selection.

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 all annotations set to false, the description carries the burden of behavioral disclosure. It adds the key behavior: it returns scored and ranked options with reasoning. It does not mention side effects or auth requirements, but for a decision-support tool this is likely computational; the description provides meaningful context beyond the bare annotation 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?

The description is extremely concise: two short sentences. It is front-loaded with 'Decision support' and immediately states the action and output, with no wasted words.

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 relatively simple tool with 4 parameters and no output schema, the description provides the core purpose and return value. It could mention the weighting behavior in more detail, but the essential information for invocation is present.

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 each parameter already has a clear definition. The description reinforces the relationship between options, criteria, and weights but does not add substantive detail beyond the schema. Baseline 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?

The description clearly states the tool's function: 'rank options against weighted criteria' and specifies the output ('scored and ranked options with reasoning'). The verb 'rank' plus the resource 'options' is specific and distinguishes it from sibling tools like analyze, reason, and review.

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 implies use for decision support when you have options and criteria, but it does not explicitly state when to use this tool versus alternatives or provide any exclusion criteria. The context is clear enough but lacks direct comparative guidance.

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 indicate non-read-only behavior, and the description adds concrete behavioral detail about the result ('step-by-step analysis with confidence score and recommendations'). It does not disclose cost or non-determinism, but pricing is encoded in the reasoning_depth parameter schema, so the description offers adequate additional context beyond 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?

The description is a single, front-loaded sentence that efficiently conveys both the action and the expected result. No unnecessary words, making it highly concise and well-structured.

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 description is adequate for a simple tool but lacks an output schema and only vaguely specifies the response format. It does not explain how to choose reasoning_depth or how this tool relates to its siblings. For a 5-parameter tool with no output schema, this leaves meaningful gaps in actionable context.

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%, so each parameter already has a description. The tool description does not add meaning beyond aligning with the 'question' parameter and implying the reasoning process; it offers no extra detail on did, domain, context, or reasoning_depth. Baseline 3 is appropriate since the schema carries the semantic load.

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 function with a specific verb ('Submit a question or problem') and resource, and specifies the output ('Returns step-by-step analysis with confidence score and recommendations'). It is unambiguous but does not explicitly differentiate from sibling tools like hiveconsult_decide or hiveconsult_review, so it misses full distinction.

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 implies usage for questions or problems requiring structured reasoning, but it provides no explicit guidance on when to prefer this tool over alternatives such as analyze, decide, or review. There are no exclusions, alternatives, or contextual triggers, leaving the agent to infer suitability from the purpose 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?

Annotations indicate readOnlyHint=false, suggesting the tool may have side effects, but the description implies a harmless review process and does not address any side effects, output storage, or permissions. Given the annotation contradicts the intuitive read-only nature of 'review' without explanation, the description fails to provide the necessary behavioral clarity.

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?

The description is a single sentence that front-loads the core action and outputs. Every word contributes to understanding, with no filler or redundant content.

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, but without an output schema the description must explain return values (it does list them). However, it omits side-effect disclosure, usage differentiation from siblings, and any input constraints beyond the schema. It is adequate for a basic review tool but leaves gaps in operational context.

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 schema already provides 100% parametric coverage with descriptions and an enum for review_type. The description reinforces the enum values in prose, but adds no new details about did or content format, so it only marginally enhances schema semantics.

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 performs reviews of specific content types (code, contracts, documents, strategies) and returns concrete outputs (issues, recommendations, risk score). It effectively communicates a specific verb and resource, though it does not explicitly differentiate from sibling tools like analyze or decide beyond implying the review focus.

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 guidance is provided on when to use this tool versus sibling tools (analyze, decide, reason). There are no prerequisites, exclusions, or alternative recommendations. The description simply states what it does, leaving the agent to infer usage context.

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