get_io_stats

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

Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds behavioral context beyond these by specifying that it warns when average latency exceeds a 20ms threshold, which is useful for setting expectations. This additional detail justifies a score above the annotation-only baseline.

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 two sentences, immediately states the core purpose, and includes only relevant detail (the warning threshold). There is no redundancy or filler, making it appropriately concise and well-structured.

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?

The tool is simple with one optional parameter, rich annotations, and an output schema, so the description need not explain return values. It covers purpose and a key behavioral detail, making it adequately complete for an agent to select and invoke correctly. Slight gap: no mention of output granularity (per-file vs aggregated), but this is not critical given the output schema.

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 input schema fully documents the only parameter (database_name) with a description and default value, so the description adds no further parameter-specific information. Schema coverage is 100%, meeting the baseline for this dimension.

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 tool's function with a specific verb ('Get') and resource ('per-file I/O stats'), enumerating key metrics (read/write latency, throughput, stall times). This distinguishes it from sibling tools like get_wait_stats which focus on waits, and get_storage_diagnostics which focus on storage-level issues.

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 description implies usage for investigating I/O performance by listing relevant metrics and mentioning a warning threshold, but it does not explicitly state when to prefer this tool over alternatives or provide exclusions. With many diagnostic siblings, clear guidance would be valuable, but the context is implicitly understood.

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