session_agent_reuse

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly states what the tool never does: it never stores or reads prompts, responses, hidden thinking or transcripts, and never spawns an agent. This is specific and useful. It does not disclose whether the tool mutates checkpoint state or how recommendations are delivered, but the core privacy and side-effect boundaries are well covered.

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?

The description is two tight sentences with no filler. The first sentence leads with the action and decision options; the second adds valuable boundary constraints. Every sentence earns its place, though the term 'refresh-delta' is assumed to be domain-known.

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 tool with six parameters, five required, no output schema, and no annotations, the description covers intent and safety but leaves critical operational gaps: parameter meanings are unexplained, and the structure of the returned recommendation is not described. An agent would struggle to construct a correct call solely from this description.

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 0%, and the description does not explain any of the six parameters. Some names like session_id and project_id are self-evident, but task_fingerprint, role_capability, source_revision, and independent_review are left entirely unexplained. The description fails to compensate for the lack of parameter documentation.

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 description states a specific action ('Recommend') and names the concrete decision outcomes: reuse, refresh-delta, or a fresh agent from compact technical checkpoint state. It clearly distinguishes this as a recommendation-only tool by saying it never spawns an agent, but it does not explicitly differentiate itself from the session_checkpoint_* siblings or other session-related tools.

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?

The description implies the tool is used when an agent-reuse decision is needed based on checkpoint state, and the mention of 'reuse, refresh-delta or a fresh agent' covers the decision space. However, it gives no explicit guidance on when to use this tool versus checkpoint read/write tools or other sibling tools, and it provides no exclusions or prerequisites.

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