kernel_agents_stats

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

No annotations exist, so the description carries the full behavioral burden. It does useful work by disclosing what the response contains (success rate, avg tokens, top tools, common errors, learnings), which is meaningful since there is no output schema. It omits any statement of time window, scope of aggregation, behavior for unknown or inactive agents, and cost/limits of the read.

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?

A single front-loaded sentence with a colon-delimited list of metrics; every element earns its place. Slightly denser than necessary but no redundant wording.

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 no-annotation, no-output-schema read tool, the enumeration of returned metrics is the right compensation and largely covers 'what comes back'. Completeness is held back by the absence of temporal scope (all-time vs recent window) and any note on what happens when the agent has no data.

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 parameter (agent_id) and schema description coverage is 100%, so the schema already documents it. The description adds no format, sourcing, or lookup guidance for the identifier, which meets the baseline for a fully covered single-parameter 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?

States a specific verb+resource ('Get performance stats for an agent') and enumerates the metrics returned: success rate, avg tokens, top tools, common errors, learnings. That is enough to distinguish it from a generic stats tool, though it never explicitly contrasts with close siblings like kernel_agents_decision_stats or kernel_brain_stats.

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?

There is no when-to-use guidance, no prerequisites, and no routing to alternatives such as kernel_agents_decision_stats for decision-specific metrics or kernel_agents_history for raw activity. The agent must infer that this is the read-only analytics entry point from the description alone.

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