ct_diagnose

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

With no annotations provided, the description carries full burden and does an excellent job: it declares the tool is read-only, lists specific probes, mentions required environment variables and allowlist, and explains the behavior when exec is disabled. No hidden side effects are implied.

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 three well-structured sentences, starting with the key purpose and conditions. Every sentence provides essential information without redundancy or fluff.

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?

The description covers the two-part output (API + in-container battery), lists probe types, and explains the runtime dependency. The output schema exists, so detailed return values are not needed. However, it could briefly note what 'advisory flags' are, but overall it is sufficiently complete for a diagnostic tool.

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 description coverage is only 25% (only proximo_target has description). The tool description does not explain the meaning or syntax of ctid, kind, or node parameters beyond their names. The description adds no parameter-level guidance, leaving the agent to infer from context. This is insufficient given low schema coverage.

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 gathers 'what's broken' evidence for a container, distinguishing it from siblings like ct_logs and ct_exec. It specifies the scope (API status + in-container battery) and conditions for full vs partial execution.

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 explains when the tool can return full results (with exec enabled) and that it works partially otherwise, disclosing skipped probes. It references ct_logs for the allowlist context. However, it does not explicitly state when not to use this tool, though the read-only nature and diagnostic purpose are clear.

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