Read a task's activity

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

Annotations already declare this a safe, idempotent, closed read, so the description doesn't need to re-argue safety. It adds ordering ('newest first'), the one-line-per-change shape, the effect of response_format='detailed', and the presence of next_cursor for pagination — useful context beyond the annotations. The only miss is not stating that cursor must be reused with the same limit (that detail lives in the schema instead).

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?

Three sentences, front-loaded with the core behavior, then alternatives, then return shape — no filler. The explicit output-shape sentence is slightly redundant given the output schema exists, but it's compact and helps set expectations before the call.

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?

With annotations covering safety, a full schema, and an output schema, the description supplies everything an agent still needs: what the history contains, ordering, pagination via next_cursor, detailed mode, and sibling disambiguation. Nothing material is missing for correct invocation.

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%, so the schema already documents task_id format, limit bounds, cursor semantics, and the concise/detailed enum. The description's note that 'detailed' adds changed field paths and its mention of next_cursor largely restate that, adding little new meaning. Baseline 3 is appropriate for full coverage.

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 and resource with scope: 'returns the activity (change history) of one task: who changed what and when'. It immediately distinguishes itself from heliyos_records_events (other record types) and heliyos_runs_list (worker runs), so an agent can route without reading sibling schemas.

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?

Explicitly names two alternatives and the condition that selects each: heliyos_records_events for company/person/deal and heliyos_runs_list with task_id for what workers did. It also implies this tool is for task-level change history, leaving no ambiguity about when to pick it.

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