observe_system

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

With no annotations, the description carries the behavioral burden. It discloses that the call 'costs nothing' (no budget penalty) and is a read operation. It could further clarify absence of side effects, but the 'read' phrasing and cost disclosure cover the most critical behavior for an agent deciding whether to call this 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?

Two crisp sentences with no fluff. The first sentence front-loads the action and lists concrete data items; the second sentence gives a clear directive. Every word adds value.

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?

Despite having no output schema, the description lists exactly what information the agent will receive (glyph alphabet, code length, budget, diagnostics legend, probe history). This is sufficient for a zero-parameter observation tool and aligns well with the sibling tools' actions.

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 tool has zero parameters, so the baseline is 4. The description adds no parameter details, but none are needed. The schema is empty and fully covered, so this dimension does not require compensation.

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 purpose: to read the lock's state, including the glyph alphabet, code length, attempt budget, diagnostics legend, and probe history. It uses a specific verb ('read') and resource ('lock'), and the enumeration of contents distinguishes it from sibling tools like probe and submit_solution.

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?

Explicitly instructs 'Call this first -- it costs nothing,' providing clear timing relative to other actions. This gives strong guidance on when to use the tool versus alternatives, and the mention of zero cost helps the agent decide to invoke it before any costly operations.

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