sassy_observability_metrics

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

Annotations already provide readOnlyHint, idempotentHint, and destructiveHint. The description adds valuable context beyond that: counters are in-memory since server start, and cpu/memory/disk fields are conditional on the optional psutil dependency. Minor gaps remain, such as whether counters reset on restart being slightly implicit, but the added context is substantial.

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 front-loaded with 'Read-only' and the core metric summary, and each sentence earns its place: field list, optional dependency note, parameter clarification, use cases, and sibling alternative. There is no filler or redundant restatement.

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?

With no output schema, the description carries the burden of explaining return values and does so well by listing all fields and explaining conditional presence of the psutil-dependent metrics. It also covers use cases and the sibling alternative. Minor omissions like timestamp format/version scope and an explicit statement of JSON structure prevent a perfect score.

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?

There are no parameters, so the schema already fully covers this dimension; the description's explicit 'Takes no parameters' is clear and prevents an agent from inventing arguments. No additional parameter semantics are possible or needed, so the baseline 4 applies.

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 ('Returns'), names the resource (real-time server metrics), and enumerates the exact fields returned. It also distinguishes itself from the sibling sassy_observability_health by indicating that tool is for a simple up/down probe.

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 lists when to use: performance monitoring, capacity questions, and error-rate checks. It also names the alternative for a different need (sassy_observability_health for up/down probes), leaving no ambiguity about selection.

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