agent_sessions

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds useful context: the returned field list and the environment prerequisite about running from the project root. It leaves out pagination/limits on listing, which keeps it short of a 5.

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 sentences, zero filler, and the primary list behavior is front-loaded ahead of the conditional read mode and the projectPath note.

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?

No output schema exists, but the description compensates by naming the returned fields (id, last activity, status, checkpoint size), and it covers the prerequisite for projectPath. Only listing bounds/pagination are unaddressed.

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?

With 100% schema description coverage, the schema already documents all three parameters, including the omit-to-list semantics of sessionId. The description restates the sessionId mode switch and the projectPath precondition but adds no format or syntax details beyond the schema, so this sits at the baseline.

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 and resource ('List the sessions of a running AI agent resource') plus an explicit second mode ('read one session's checkpoint when sessionId is set'). It even enumerates the returned fields, which distinguishes it from siblings like agent_list and runtime_check.

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?

Conditions are spelled out: set sessionId to read one checkpoint, omit it to list, and set projectPath when the MCP server is not running from the project root. It does not name sibling alternatives, but the mode-selection guidance is unambiguous.

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