list_tasks

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

Declares read-only and returns JSON array. Lacks mention of any result limits, pagination, or ordering, but given no annotations, it covers core behavior adequately.

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?

Well-structured: purpose sentence, output type, filter syntax examples, sibling tool recommendations. No redundant 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?

Has output schema. Covers filtering and alternatives. Minor gaps: no mention of sort order or result limits, but sufficient for a list operation.

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?

Despite 0% schema coverage, the description extensively documents the single 'filters' parameter with syntax examples, combining rules, and default behavior.

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 'List and filter Taskwarrior tasks' and specifies read-only nature. It distinguishes from siblings like get_task (UUID lookup) and search_tasks (field-specific free-text).

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 provides when to use alternatives: 'Prefer get_task for UUID... Prefer search_tasks for free-text... Use get_task_report for named reports.' Also explains default filter behavior.

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