checkpoint_record

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

No annotations are provided, so the description carries the full burden. 'Create or update' discloses an upsert mutation, and 'with evidence' hints at a requirement. But for a tool with 23 parameters, complex behavior is undisclosed: optimistic concurrency (expectedRevision), invalidation semantics (invalidatedAt), aggregation behavior (aggregationPolicy), and evidence-level requirements (requiredEvidenceLevel) are all silently present in the schema yet never surfaced in the description.

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 with no filler — efficient and front-loaded with the action. However, the concision comes at the cost of substance: the second sentence ('Passed checkpoints are the only basis for healthy completion states') conveys philosophy rather than actionable behavior. For a tool with this parameter count, the brevity reflects under-specification rather than disciplined pruning.

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?

Completely inadequate for the tool's complexity: 23 parameters, nested objects (evidence, aggregationPolicy), six enums, and no output schema. The agent is left without knowledge of the status enum semantics, targetType meaning, checkpointKind distinctions, or the return format. Nothing in the description compensates for the absence of an output schema or the massive parameter surface.

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%, so the description must compensate — and it barely does. It maps to only two parameters: 'evidence' (the evidence array) and 'passed' (a status enum value). The other 21 parameters, including required targetType, targetId, title, and the six enums, receive no clarification. The description adds marginal value over the schema for a tool that badly needs it.

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 clear verb+resource: 'Create or update a checkpoint with evidence.' This distinguishes it from sibling checkpoint_list (listing) and checkpoint_refresh_candidates (refreshing candidates). The second sentence adds useful domain significance about passed checkpoints. However, it doesn't explicitly differentiate itself from the other checkpoint siblings by name or scoping condition.

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?

No guidance on when to use this tool versus checkpoint_list or checkpoint_refresh_candidates. No alternatives are named, and no exclusions or preconditions are given. The 'passed checkpoints are the only basis' sentence hints at domain semantics but doesn't tell the agent when to record a checkpoint versus read candidates or list checkpoints.

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