Get Run Progress

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

Beyond the readOnly/idempotent/non-destructive annotations, the description discloses the auth constraint (session or internal-token; event stream and thread state unreachable with a PAT), the semantics of stalled vs quiet, and delta-mode behavior via since_seq. This is substantive behavioral context the annotations cannot convey.

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 content is front-loaded (purpose first, then return payload, then delta mode, then auth) and every clause carries information. It is dense in a single block rather than broken into scannable segments, which costs it a point.

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?

An output schema exists so return values need not be spelled out, yet the description still gives the agent the auth prerequisite, the polling/delta mechanics, and how to interpret stalled/quiet/next_step. Nothing needed to invoke or interpret the tool correctly is missing.

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?

With 100% schema coverage the baseline is 3, but the description adds real meaning for since_seq by tying it to last_event_seq from a previous response and framing it as delta mode, beyond the schema's 'only include events with seq greater than this'. activity_limit and the ids are left to the schema.

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 gives a precise verb+resource ('Get live progress for a DeerFlow run') and enumerates exactly what is returned: status, live counters, recent activity, todo checklist, and stall/quiet detection. It is highly specific, but it never names or contrasts itself against close siblings like deerflow_run_status or deerflow_wait_activity, so an agent must infer the boundary from wording alone.

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?

Usage context is implied rather than stated: since_seq is described for delta polling and next_step points at the web UI and deerflow_cancel_run, but there is no explicit 'use this instead of deerflow_run_status when...' guidance. The alternative tools are referenced only in passing.

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