perf_sample_window

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

No annotations provided, so description carries full burden. It discloses it samples evenly-spaced points, returns raw time-series requiring delta computation, and has clamping ranges. Could be more explicit about non-destructive nature but adequately transparent.

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?

Description is structured with overview, use case, alternative, and parameter details. Front-loaded with purpose. Slightly verbose but every sentence adds value; could be tightened slightly.

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?

Given tool complexity (sampling) and presence of output schema, description is adequate. It explains the raw time-series return, no need to detail output schema structure. Could mention synchrony or side effects, but overall complete.

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 description coverage is 0%, so description must explain parameters. It does so thoroughly: duration_sec range, sample_count range, groups default prefixes. Adds significant meaning beyond schema types and defaults.

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 it 'Sample runtime statistics at a fixed cadence over a short window' and provides a specific use case ('is the proxy under pressure right now?'). It distinguishes from sibling tools like perf_hotspots by contrasting with long-term TSDB solutions.

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 tells when to use (short-term pressure checks) and when not (long-term observation, suggesting alternatives proto_hep or prometheus). Mentions caps (10 min/60 samples) to manage MCP response size.

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