lm_diagnose

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered by structured data. The description does add value by saying it gathers error history and redacted log signals and returns 'evidence and repair steps', which tells the agent what to expect back; however it says nothing about cost, latency, or whether log collection touches external systems.

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 tightly written sentences with zero waste. The scope enumeration comes first and the return-value note second, so the most decision-relevant content 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 read-only diagnostic with no output schema, the description adequately states the subject areas and the shape of the result ('evidence and repair steps'). It nonetheless leaves the include_hardware flag and the depth/expense of the diagnosis unexplained, which is a noticeable gap for a tool that probes many subsystems.

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 single parameter include_hardware has 0% schema description coverage and is not mentioned anywhere in the description. With no zero-param baseline to fall back on, the one undocumented flag leaves the agent unable to tell what enabling it changes about the diagnostic scope.

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 specific verb ('Diagnose') and enumerates the resources examined: API, server, disk, loaded models, error history and redacted log signals. That is far better than a tautology, but it never distinguishes itself from the many adjacent diagnostic/status siblings such as lm_status, lm_runtime and lm_connections, so an agent cannot confidently pick it over them.

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?

There is no guidance on when to reach for this tool versus lm_status or lm_runtime, nor any stated prerequisites or exclusions. The diagnostic intent is only implied by the verb 'Diagnose', leaving the agent to guess the trigger condition.

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