get_context_history

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

Without annotations, the description carries full burden. It indicates a read operation ('Read') and hints at immutability ('append-only provenance ledger'). However, it omits behavioral traits like authorization needs, rate limits, or whether the ledger is ordered, which limits transparency.

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 tightly packed sentences with no fluff. The first sentence front-loads the core purpose, and the second efficiently explains the key behavior. Every word earns its place.

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?

Given no output schema, the description should hint at return format (e.g., list of entries, timestamps). It explains usage well but omits what the agent receives, making it slightly incomplete for a fully autonomous call.

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%. The description adds minimal value beyond the schema for task_id and key, essentially restating the schema descriptions. Baseline 3 is appropriate as the schema already provides clear 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 clearly states the tool reads the 'append-only provenance ledger for a task's context,' specifying the verb (Read) and resource. It distinguishes from siblings like get_task_context and update_task_context by focusing on history rather than current state.

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 provides guidance on using the 'key' parameter to narrow history versus omitting it to get the newest across all keys. However, it does not offer when-not-to-use or compare to alternatives like get_task_context, leaving some ambiguity for agents.

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