Load session checkpoint

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful context beyond them by previewing the brief's contents and the "changed since saved" diff, though it says nothing about behavior when no checkpoint file exists.

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, no filler: the first delivers the action and the return contract, the second delivers the trigger. Front-loaded with the verb so an agent grasps the purpose immediately.

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?

An output schema exists, so the description need not re-explain return shape, and annotations cover the safety profile for a 2-parameter tool with zero required params. What remains — what it loads, what it returns at a glance, and when to call it — is all present.

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 the format enum is fully documented in the schema itself (brief = compact markdown, full = complete JSON), so the schema does the heavy lifting. The description's mention of a "compact brief" aligns with the default but adds no syntax or format detail beyond the schema; baseline 3.

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 (Load) and resource (.claude-checkpoint file), then enumerates exactly what the returned brief contains: goal, progress, next steps, touched files, recent commands, and changed-since files. The opposite verb makes it trivially distinguishable from the save_session_checkpoint sibling without opening either schema.

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?

"Call at the start of a session or when the user asks to resume" is an explicit, actionable trigger condition. It does not name the save_session_checkpoint alternative or state when-not to call, but for a load-only read tool the trigger is clear enough.

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