Налагоджувальний журнал

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

With no annotations present, the description carries the full burden of disclosing behavior. It reveals that the tool reads raw gateway traffic, that its availability depends on a server-side debug flag, and that it exposes content not present in normal logs. It stops short of explicit verb/read-only semantics, but the context strongly implies a non-destructive tail operation.

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?

Three compact sentences, each carrying distinct information: what the log contains, when it is written, and what unique value it offers. No redundancy or filler; the most essential fact is front-loaded.

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 two-parameter, no-output-schema tool, the description provides essential operational context: the raw content type, the conditional availability, and the extra diagnostic value. The only gap is that it does not explicitly describe the return format or what happens when debug mode is off, but the schema and the condition imply enough for a competent agent.

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 documents both optional parameters (grep and blocks) with full coverage. The description does not add any parameter-level detail, so the baseline 3 for high schema coverage is appropriate; no extra meaning is necessary or missing.

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 the tool exposes a raw gateway exchange log: request bodies, responses, and tool calls. It clearly distinguishes what this log contains (broken arguments, bloated prompts, actual gateway response text) and when it is available (GLM_DEBUG=1). This is far more informative than the title alone and differentiates it from the sibling tools.

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 clear condition for use: the log is written only when the server is started with GLM_DEBUG=1, so the agent knows to rely on this tool only in debug sessions. It also positions it as a complement to the 'usual log' by highlighting what is uniquely visible here. However, it stops short of explicitly naming alternative tools or stating when not to use it.

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