task_update

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

With no annotations, the description carries the full load and does well: it discloses gating rules (approval_needed tasks cannot reach in_progress or done without a human approval), a destructive-ish sentinel (due="" clears the date), and a human-only constraint on approved_by. It does not describe error behavior when a precondition fails or what the tool returns, which is the main remaining gap.

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?

Nearly every clause carries a distinct rule and the mutation/constraint information is front-loaded before the parameter notes. The long semicolon-chained approval sentence packs three obligations into one breath, which slightly hurts scannability but wastes no words.

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 12-parameter mutation tool with no annotations and no output schema, the description covers the high-risk semantic rules an agent needs to avoid bad writes. It stops short of enumerating status values and explaining owner_bot/approval_needed, so an agent must still guess at those fields.

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 0% across 12 parameters, and the description supplies real meaning for most of them: ask, due, evidence, approved_by, approval_source, test_results (with its shape and allowed values), actor, note. It leaves owner_bot, approval_needed, and id unexplained, and never enumerates the full set of valid status values even though it names several.

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 opening sentence gives a specific verb plus resource and enumerates the mutable fields (status/due/owner/approval_needed) and the log-append behavior, so an agent knows exactly what this tool touches. It does not distinguish itself from ambiguous siblings like task_act or task_waiting, which likely also affect status transitions.

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 rules are explicit and conditional: ask is required when moving to waiting_on_owner, approved_by/approval_source are needed to record an approval, and evidence plus test_results are needed to reach done. What is missing is routing guidance against siblings (task_act, task_waiting) for the same state transitions.

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