Health & metrics

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

Annotations only declare readOnlyHint and openWorldHint; the description adds cost profile ('fast, ~a few ms + 1 audit DB query'), a concrete cost-reduction lever (include_audit=false skips the DB query), the returned sections, and a batch-safety flag. That is behavior an agent could not derive from the annotations or schema.

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?

Labeled, front-loaded fragments (purpose → use → avoid → speed → output → batch-safe) with zero redundant text. Every clause delivers operative information an agent acts on.

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?

No output schema exists, and the description pre-empts that by listing the result sections (health, server, corehost, capability, queue, caches, shells, metrics, audit). Cost, safety, scope, and invocation guidance are all covered for a zero-required-argument 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 coverage is 0% for the single include_audit boolean, so the description must carry the load — and it does, explaining the semantic effect (skips the audit DB query) and thereby implying the default is true. It stops short of stating the default or that the parameter is optional, so not quite a 5.

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?

Opens with a specific verb+resource ('Server diagnostics') and enumerates exactly what it inspects: corehost/data dir/audit DB, capability, queue depth, cache hit-rate, running shells, p50/p95 metrics. The 'Avoid when: you just need to read/write files normally' line separates it from the many file-oriented siblings in one stroke.

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?

Has an explicit 'Use when' clause naming three concrete triggers (debugging slowness/errors, verifying backend/DB/audit before reporting, inspecting this session's cache/metrics) and an explicit 'Avoid when' clause pointing to normal file I/O. The when/when-not pair leaves nothing to inference.

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