get_performance_monitors

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

Annotations already declare the read-only, non-destructive profile, so the description is free to add real context: values are timestamped and carry units, output is a point-in-time snapshot rather than a profiler trace, and render metrics are absent under headless. Those are behavioral facts the annotations do not encode.

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 sentences, no filler, with the core action stated first and the caveats after. Every clause carries information an agent would otherwise have to discover by trial.

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?

An output schema exists, so return values need not be explained, and the description covers the headless limitation and the snapshot granularity. What remains missing is the relationship to the other sampling tools, which is the one real gap.

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?

Only one optional parameter (sessionId) and schema coverage is 100%, so the schema already explains its purpose and the MCP-version requirement. The description adds nothing about it, which is the expected baseline 3 when the schema does the work.

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?

"Read timestamped runtime Performance monitor values with units" gives a specific verb and resource, and the snapshot-vs-profiler clause rules out one misreading. It stops short of differentiating from the similar sibling sample_performance, so an agent still has to guess which sampling tool applies.

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 headless caveat ("Render metrics are unavailable under headless") is a useful exclusion, but there is no explicit statement of when to pick this over sample_performance or sample_node_properties. Usage is only implied by the snapshot framing.

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