oc_journal_compact

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

Annotations already indicate read-only and idempotent. The description adds: 'Defaults to deterministic recent_k', 'checkpoint_only returns milestone-flagged entries', 'sampling forwards to host LLM and returns unsupported status', and 'OpenChrome never uses its own LLM'. No contradictions.

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 a single dense paragraph, but it is well-organized with front-loading of purpose, then defaults, then strategy details. It could benefit from visual structure like bullets, but remains clear and efficient.

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?

The description thoroughly covers inputs and strategies but lacks explanation of the return value format for strategies other than sampling. The output is described as 'compact model-friendly summary', which is vague. Given no output schema, more detail would help.

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 coverage is 100% (all 4 parameters described in schema). The description adds extra context: session_id explains filtering behavior after cross-session window, recent_steps and token_budget have defaults, strategy enum values are explained.

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 clearly states the tool compresses journal entries into a summary, with specific verb 'compress' and resource 'journal entries'. It distinguishes from siblings like oc_journal by stating 'compact model-friendly summary' and detailing strategies.

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 explains when to use each strategy (recent_k, checkpoint_only, sampling) and notes the sampling capability requirement. It does not explicitly state when to avoid this tool, but the purpose and sibling context make it clear.

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