update_task

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

With no annotations, the description carries the behavioral disclosure burden. It does disclose one meaningful behavior: 'preserving done state', which clarifies that rewriting text does not alter completion status. However, it omits other behavioral traits such as the agent-tag side effect, the expect guard semantics, and the default plan_path lookup, so transparency is partial.

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 description is very compact and front-loads the core purpose before presenting usage patterns. Both sentences earn their place with no filler. The shorthand notation is terse but still readable; a little more explicitness about the omitted modes would be the only improvement.

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?

The tool has 10 parameters, multiple addressing modes, a required 'version' parameter, and no output schema or annotations. The description covers only the singular and changes modes, omitting the valid tasks and indexes arrays, and does not explain the required 'version' parameter, which has no schema description either. This leaves an agent without enough context to safely invoke every supported usage.

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 90%, so the baseline is 3, but the description adds relational parameter semantics: it groups 'text + index/task' for a single task and 'changes[{text, index|task, expect?}]' for several tasks, making mode exclusivity explicit. This goes beyond the flat schema properties and helps an agent understand which parameters combine. It omits the tasks and indexes arrays, though those are already described in the schema.

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 clearly states the verb and resource: 'Rewrite task text', and adds the important qualifier 'preserving done state', which distinguishes it from state-changing siblings like complete_task and reopen_task. It does not fully enumerate all addressing modes (tasks and indexes arrays are omitted), but the core purpose is unambiguous.

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?

There is no explicit guidance on when to prefer update_task over sibling tools such as add_task, append_prose, or complete_task. The description gives some within-tool usage patterns for single vs. several tasks, but it does not provide decision rules or exclusions relative to alternatives.

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