task_act

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

With no annotations, the description carries the behavioral burden and does so well: it discloses the default actor (BACKLOGR_OWNER), the status effect of each action, that 'later' is note-only, that 'question' leaves status unchanged but flags an open_question for the owner bot, and that undo reverts the last act only if nothing changed. It omits permission requirements and what happens to the reason field for actions other than 'later'/'question'.

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 lead sentence establishes the concept immediately and the action taxonomy follows in a compact, scannable pipe-delimited list. The final sentence about history logging is short and informative. The dense run-on packing of five action definitions into one paragraph slightly hurts readability but nothing is wasted.

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 4-parameter mutation tool with no annotations and no output schema, the definition covers the actor, all action semantics, side effects, undo conditions, and the audit trail. Missing pieces are the actual return payload and error behavior (e.g. what happens when undo is attempted after a change), but the call-critical information is present.

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 0%, so the description must compensate, and it largely does: it defines the full action value set with per-value semantics, establishes 'by' as the acting person with a documented default, and explains that 'reason' is mandatory for 'later' and constitutes the question text for 'question'. Only 'id' is left unspecified, which is self-evident from the task-focused siblings.

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: a single-call 'action' on a task, attributed to a person, with the enumerated action values and their outcomes. This is clearly not task_create/task_update-style editing. It falls short of a 5 because it never names the sibling it should be preferred over (e.g. task_update or task_flags), leaving the boundary implicit.

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?

The per-action breakdown (later / done / na / question / undo) effectively tells the agent which action to pick for a given intent, and the 'dashboard buttons' framing implies interactive use. However there is no explicit guidance on when to choose this tool versus task_update or task_flags, and no stated precondition for 'undo' beyond 'if nothing changed since'.

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