Read a whole task

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

With no annotations, the description carries the full behavioral burden and does well: it describes the returned contents at a high level, explains that `fields` limits the response, and notes that closed tasks return `closed` and a `notice` and are immutable history. It does not cover permissions, error behavior, or limits, which keeps it from a 5.

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 front-loaded and every sentence carries relevant information, but it is verbose and relies on idiosyncratic phrasing such as 'grey hints,' 'mending,' and 'what it keeps.' Those metaphors make the description less crisp than it could be, even though the overall structure is logical.

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 whole-task read with no output schema, the description gives a reasonably complete picture of what comes back, including document content and closed-task behavior. It is not exhaustive about response shape or failure modes, but it covers the major things an agent needs to call the tool correctly.

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 already 100%, but the description adds useful meaning beyond the schema: `fields` is framed as the way to retrieve only named parts and to inspect one thing without pulling a long journal. It also connects `part_of` to the sibling `find` behavior, giving the parameter practical context.

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 frames the tool as returning everything held by one task, including description, steps, journal, parts, kept items, and document. It is more specific than the generic name `read` suggests and helps distinguish the whole-task read from `find` by noting that `find` with `part_of` retrieves parts of any task.

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?

It explicitly says to use this before adding a note and before mending anything, and explains the `fields` option for checking one thing on a task with a long journal. It also names `find` with `part_of` as the alternative for retrieving parts across tasks, so when to use this versus another tool is clear.

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