task

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

With no annotations, the description must carry the behavioral burden, and it partially does: it conveys the state transition of each action ('release: give it back', 'done: finish') and the social obligation that done takes a one-line change note. It says nothing about irreversibility of done, permissions, concurrency/race behavior on take, or error handling — significant omissions for a mutation-heavy tool.

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?

One lead sentence plus a tight action-by-action list; no filler, and the overall scope is front-loaded before the per-action detail.

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?

For a nine-action polymorphic tool with no output schema, the description covers inputs and action semantics but says nothing about what 'list' returns, what keys look like beyond the schema example, or what success/failure responses look like — leaving the agent to guess at outcomes.

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 the baseline is 3, but the description adds value by mapping actions to parameters (which actions need a key, that note is required for done as 'what changed for others') — a mapping the schema does not make explicit since only 'action' is required.

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 specific verb+resource ('Work the task board') and then enumerates all nine actions with one-line meanings, so an agent knows exactly what each mode does. However it never distinguishes itself from the similarly-named sibling 'claim', which overlaps with the 'take: claim an open task' action — a real ambiguity for tool selection.

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?

Each action carries its own contextual guidance (e.g., 'start: begin (only when its dependencies are done)', 'accept/decline: answer a task proposed to you', 'assign: give a task to a teammate'), which is unusually good routing within the tool. It stops short of saying when to use this tool versus alternatives like 'claim' or 'plan'.

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