diagnostics

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

With no annotations, the description carries the full burden and does well: it declares the operation read-only, enumerates what is deliberately NOT returned (PTY contents, credentials, path, environment values), and explains the caller_status gate that can deny agent sending. It does not describe output format details beyond 'machine-readable JSON', but the safety profile is clearly conveyed.

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?

Efficient and front-loaded: the read-only nature and safety boundary come first, followed by the hook-status behavior. It is dense but each clause (safety exclusions, caller_status effect, setup remedy) earns its place.

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 zero-parameter, no-output-schema diagnostic tool, the description is fairly complete: it covers the read-only guarantee, the data-safety boundary, and the actionable caller_status behavior. Minor gaps remain around exactly what diagnostic categories are returned, but nothing essential for correct invocation is missing.

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 takes zero parameters, so per the rubric the baseline is 4. There are no parameter semantics to document or omit, and nothing in the description contradicts the empty schema.

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+resource ('read-only 診断' / diagnostics) and scopes it to Factory, returning machine-readable JSON. It is reasonably distinguishable from the pty_* siblings, though it never explicitly names an alternative tool. The exact scope of what is diagnosed remains a bit general.

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 implies usage by describing the caller_status=setup_required condition and instructing to run aiterm-setup, which is actionable context. However, it never states explicitly when to call diagnostics versus the many sibling tools. Usage is implied rather than directed.

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