add_clause

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

The description discloses several behavioral details: state accepts both code and Russian name, group has specific allowed values, and every changes the semantic from 'any of' to 'all'. It does not, however, mention side effects, reversibility, or any side effects of adding a clause, and annotations are absent. It adds some context but leaves the operation's overall effects under-specified for a mutation tool.

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 multi-part sentence that front-loads the primary purpose and then packs parameter-specific details. While it is a bit dense and uses a run-on structure, it avoids fluff and communicates the core intent first. It could be split for readability, but it remains acceptably concise.

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 mutation tool with 8 parameters, an output schema (which relieves return-value description), and no annotations, this description is incomplete. It covers some parameter semantics but omits context on how handle/owner/tag/join are used, any prerequisites, or how the added clause integrates with existing logic. An agent would struggle to construct a valid call without additional schema or background knowledge.

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 8 parameters and 0% schema description coverage, the description must compensate heavily. It adds meaning for 'group' (enumerating valid values), 'state' (explaining accepted formats), 'every' (explaining the semantic difference), and 'targets' (selection based on target type). However, it does not explain 'handle', 'owner', 'tag', or 'join', leaving half the parameters under-specified despite the description's partial help.

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 states a specific action — adding a condition to the logic of a device or object — with a clear subject and resource. It distinguishes from sibling tools like add_device or add_plan by the domain (logic of device/object), though it doesn't explicitly contrast those alternatives. The verb and resource are clear enough for an agent to understand the operation's 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?

The description offers no guidance on when to prefer this tool over alternatives. It only explains internal behavior (group options, state formats, every flag, target selection) but never states conditions like 'use this when you need to add a condition to existing logic' versus other tools. No explicit when-not or alternative routing is provided.

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