Управление динамическими целями

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

Annotations already declare destructiveHint=true and openWorldHint=true, so the destructive profile is covered. The description does not add anything beyond the enum, such as irreversibility detail (though the schema notes delete is irreversible) or bidding behavior on set_bids.

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 compact sentence enumerating all supported actions. It is appropriately sized and front-loaded, with no filler, though it is not broken into structured when-to-use segments.

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 multi-action mutation tool with rich schema coverage and destructive annotations, the description is minimally viable. It lacks routing to sibling tools and does not clarify action-specific prerequisites, leaving modest gaps.

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 parameters are fully documented in the schema. The description adds no parameter detail beyond the action verb list, which matches the baseline 3 when the schema carries the 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?

States a clear set of verbs (create, change bids, stop, resume, delete) applied to dynamic targets. It distinguishes itself from the sibling list_dynamic_targets by being the mutating counterpart, though it does not name that sibling explicitly.

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 action list implies when each mode applies, but there is no explicit guidance on prerequisites or when to prefer this tool over siblings like list_dynamic_targets. Usage must be inferred from the enum values.

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