List agent sessions

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

readOnlyHint=true already establishes the safe-read profile. Beyond that the description adds a real behavioral filter (only messageable sessions, not every process on the machine) and discloses the returned fields (names, refs, working directories, status), which is valuable given there is no output schema. It omits ordering, staleness, and whether the caller's own session appears.

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?

One sentence, front-loaded with the verb and resource, then scope, then return fields. No filler and nothing buried.

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-only list tool with no output schema, the description covers purpose, scope, and returned fields, and annotations cover safety. Minor gaps remain around result ordering and whether the listing can be incomplete or stale, but nothing essential to calling it is missing.

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 and the schema is empty, so per the baseline a 4 applies. The description correctly says nothing about parameters, avoiding noise.

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 concrete verb (list) and resource (Claude Code / Codex sessions on this machine), plus the scoping condition 'that you can message'. This is far clearer than the bare name 'list_peers', though it never names or contrasts with the nearest sibling (list_channels, list_tasks), so it stops short of full differentiation.

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 only implied: 'that you can message' hints these are the peers you may target with send_message/ask, but there is no explicit when-to-use, when-not, or named alternative. An agent can infer the workflow but must do the inferring itself.

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