task

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

With no annotations, the description carries the full burden and does well: it discloses storage ('type=task'), the auto-archive lifecycle ('archives itself once every item is done or dropped'), and generation of stable item keys (i1, i2) consumed by task_item(). It omits any mention of permissions, failure modes, or whether the task is visible to other sessions.

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?

Front-loaded with purpose and lifecycle, then parameter-by-parameter detail in short labeled blocks. A few asides (the repeated 'See note()', the remark about the type name not being auto-added) add length, but each carries actionable guidance rather than filler.

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 7-parameter write tool with no annotations and no output schema, the description covers the creation semantics, limits, key generation, and lifecycle well. The two gaps are the undocumented domain and session parameters, which an agent would have to guess at.

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%, so the description must compensate, and it documents five of seven parameters with real semantics: title (one line, ≤120 chars), goal, items (one per line, ≤50 items of ≤300 chars, keyed i1...), also (comma-separated cross-cutting domains), and tags (synonyms not in the body, with a rationale). It leaves domain and session entirely unexplained.

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+resource and scope: 'Open a task: a goal and a checklist, kept until its items are closed.' It also names the sibling tools that operate on the created task (task_item, task_add, task_comment, pending), so an agent can distinguish it from those without opening a schema.

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?

Explicitly routes follow-up work: 'Work it with task_item(), grow it with task_add() and discuss it with task_comment(); ... pending() lists the open ones.' This tells the agent both when to use this tool and which alternatives to use for the adjacent operations.

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