watch

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does not state whether the snapshot is a read-only retrieval, whether it mutates or marks messages as read, what permissions are needed, or what the result contains. The single sentence is grossly inadequate for an unannotated 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?

It is a single short sentence with no waste, but it is front-loaded with the vague term 'Snapshot' rather than the concrete action. Brevity is achieved at the cost of clarity.

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?

Zero parameters, no annotations, no output schema, and 48 sibling tools. Without annotations, the description must carry the full behavioral burden. It fails to explain the return format, the meaning of 'last', whether the snapshot is persisted or ephemeral, or how it differs from messages/dialogs. It is not sufficient for an agent to call correctly.

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?

Parameter count is 0, so the baseline is 4. However, the description references a 'target' parameter that is absent from the schema, which is confusing and slightly undermines its usefulness.

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 mentions 'snapshot the last messages of a chat, or the latest dialogs' but does not actually state the core action. The word 'Snapshot' is vague; it could mean read, retrieve, copy, or capture. It references a 'target' parameter that does not exist in the schema, and does not distinguish this tool from siblings like read, messages, or dialogs.

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 gives a fallback ('when target is omitted') but no positive condition for when to use this over read, messages, or dialogs. No when-not-to-use or alternative selection guidance is provided.

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