perf_stats

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

With no annotations supplied, the description carries the full burden and does reasonably well: 'report' plus 'for the running server' establishes a read-only snapshot of server-internal counters with no arguments and no mutation implied. It also adds diagnostic context beyond the mechanics by explaining what a high credential-broker or role-cache miss rate indicates, though it does not state whether counters are cumulative since start or reset per call.

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?

Three short sentences, each doing distinct work: what is returned, what question it answers, and how to read the numbers. The purpose is front-loaded in the opening clause and there is no filler or repetition.

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 zero-parameter read tool with an output schema, the description is nearly sufficient: it explains the data collected and how to interpret two key signals, so return values need not be documented. The remaining gap is routing, since the presence of the sibling cache_status means an agent still has to guess which of the two cache-related tools to call.

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 tool takes zero parameters, so the baseline is 4 and there is nothing for the description to disambiguate. The description correctly implies a no-argument call scoped to the running server, matching the empty schema.

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 first sentence gives a specific verb plus resource: report cache hit/miss counts and executor sizing for the running server. It is clear what is measured, but it never distinguishes itself from the sibling tool cache_status, which an agent would plausibly confuse with this one.

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?

Usage is conveyed indirectly through a scenario ('why was that fan-out slow?') and an implicit alternative ('without turning on debug logging'), which gives an agent a real trigger to reach for this tool. However, there is no explicit statement of when NOT to use it, and the obvious sibling cache_status is never mentioned as an alternative or complement.

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