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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds that results are scoped to a single kernel and include multiple participant types, but says nothing about ordering, pagination, or whether history is truncated beyond the default limit.

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?

Two short sentences with the core action front-loaded and no filler. The second sentence is mildly redundant with the first but does usefully enumerate the participant types.

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 simple two-param read tool with an output schema absent but trivial return semantics, the definition is adequate but leaves open result ordering and pagination behavior. Nothing an agent needs to invoke it is missing, but nothing extra is provided either.

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 100% and both parameters (kernelId, limit with default 50) are documented in the schema. The description adds kernel scoping context but no syntax or behavioral detail beyond what the schema already provides, so baseline 3 applies.

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 ('Get') and resource ('chat history with a kernel') and clarifies the returned content is messages between agents, operators, and users for a specific kernel. It does not name or differentiate itself from the sibling pcc_chat_send, which is the closest alternative, so it lands just short of a 5.

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 implied by the read-oriented framing and the presence of pcc_chat_send as a sibling, but the description never states when to use this versus sending or listing conversations (e.g. list_conversations). No exclusions or prerequisites are given.

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