a4a_dialogue_history

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

With no annotations, the description carries the full burden, and it does disclose real behavior: results are bounded, paging is backwards, file references are hidden, and history loading never fetches blobs. However, 'checkpoint' is left ambiguous — it is unclear whether calling this advances/mutates a checkpoint or merely reads up to one, and nothing states whether history entries are consumed or marked as read.

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?

Four short sentences, front-loaded with the core action, then paging rule, then the attachment caveat. No filler or repetition.

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?

Paging and attachment handling are covered, but with no annotations, no output schema, and 0% parameter documentation, the description should also state what a page contains and whether the checkpoint is mutated. The 'before' vs 'next_before' mismatch leaves a concrete gap for a 2-parameter tool.

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 0% and neither parameter is described. Worse, the description names 'next_before' while the schema parameter is 'before', which can mislead an agent into passing a nonexistent argument. Only the 'zero selects the latest page' clause maps usefully to 'before'; lease_token gets no meaning beyond the required flag.

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 concrete action (read bounded history and checkpoint) on a specific resource, scoped to 'the current lease', which separates it from sibling dialogue tools like a4a_dialogue_send or a4a_dialogue_checkpoint. The phrase 'untrusted history and checkpoint' is jargon-heavy but recognizable to an agent already in the a4a dialogue flow.

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?

Implies a precondition (an active lease) and routes blob retrieval to a separate a4a_open_file call, which is useful routing. It never says when to use this over a4a_read_private or a4a_inbox_next, nor how a lease is obtained (a4a_dialogue_lease exists), leaving the selection decision implicit.

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