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

Annotations only declare readOnlyHint=true, but the description adds substantial behavior: blocks up to 45 seconds, returns outcome plus per-step outcome and first failing step, returns timed_out with last observed state, and notes nothing notifies the client when a run ends later. It also discloses that timeout_minutes is ignored here and that the repo must already be connected.

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?

Purpose is front-loaded, then scoping, then the timed_out continuation protocol, then the log follow-up. Dense but every sentence carries operational weight; no filler.

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?

No output schema exists, so the description must describe returns — and it does (settled run with outcome, step outcomes, first failing step; or timed_out with last state). For a 7-param polling tool with a safety annotation, nothing needed for correct invocation 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?

Schema coverage is 100% so baseline is 3, but the description adds real meaning beyond the schema: run_id accepts a UUID or a run number (3630 for run #3630), branch disambiguates head_sha lookups, and timeout_minutes is ignored here. Only minor gaps remain.

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+resource: 'Wait for an Ankra Pipelines run... to conclude.' Clearly distinct from siblings like watch_workflow_run and get_pipeline_step_logs, and names the exact entity being watched.

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 instructs re-calling watch_pipeline_run with the returned run_id on timed_out, names get_pipeline_step_logs as the follow-up for failing logs, and states the run is identified by head_sha or run_id with branch disambiguating. When and how-to-continue are fully specified.

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