get_performance_monitors

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

No annotations are provided, so the description carries the full burden. It discloses that the output is a raw dump, units for time/memory/VRAM, and filtering behavior. It does not explicitly state read-only or no side effects, but 'dump' implies non-destructive. The 'not a running game' clarification adds context but more explicitness would be better.

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?

Single sentence, front-loaded with the core action, then units, then filter. Every clause adds value with no filler. Excellent conciseness for a simple tool.

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 one-parameter tool with no output schema, the description covers key aspects: what it dumps, scope, units, and filtering. It could be more explicit about the output format (e.g., a map of key-value pairs), but 'key prefix' implies a dictionary. Given the tool's simplicity, this is adequate.

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 schema has one parameter 'category' with no description (0% coverage). The description's phrase 'optionally filtered by key prefix' directly explains the purpose of the 'category' parameter, adding essential meaning beyond the schema and compensating for the lack of schema documentation.

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?

The description clearly states the action 'Dump' and the resource 'raw Performance monitors of the editor process', and explicitly scopes it to the editor process (not a running game). This distinguishes it from sibling tools that might target game performance or high-level statistics.

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 provides context that this is for the editor process, not a running game, and mentions optional key prefix filtering. However, it does not name alternative tools for game performance or specify when not to use it beyond the 'not a running game' parenthetical.

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