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

With no annotations, the description carries the burden and does add real behavioral detail: the deterministic ordering (priority, then errors, then age) and the fact that exclude_relative_ids is per-call and does not mutate piece state. It stops short of stating permissions, whether a null/empty result is possible, or what object is returned.

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?

Two sentences, no filler, and the core behavior and ordering are front-loaded before the exclude_relative_ids advice. The second sentence is long but each clause carries load, so it stays efficient.

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 should say what comes back (a piece object? null when nothing is available? blocked/deferred handling?), and it does not. Given a plain 3-parameter read tool with no annotations, this is an adequate but incomplete definition.

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; the description goes beyond the schema by explaining the intent behind exclude_relative_ids (the 'stuck on the same piece' scenario) and by framing project_relative_id as an optional filter. This adds actionable meaning rather than repeating the field docs.

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 ('Get the next task or story to work on') and even encodes the selection algorithm (highest priority, errors first, oldest within priority). It is clearly distinguishable from ListPiecesTool/GetPieceTool by its 'next actionable item' semantics, though it never names those siblings to draw the contrast explicitly.

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?

Gives a concrete usage context: optionally filter by project, and when you are waiting on something for a piece without formally blocking it, pass exclude_relative_ids to avoid looping. It does not, however, mention when to prefer BlockTaskTool instead of this skip-loop pattern, leaving one relevant routing decision to inference.

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