List tasks

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

No annotations exist, so the description carries the full burden and does reasonably: it discloses the default open-only filter, the exact returned field set (and what is omitted), and the override semantics of `filter` over includeDone. It is silent on pagination behavior and rate limits, which leaves some behavioral 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?

Three information-dense sentences with no filler: scope first, then return shape and the get_task handoff, then the default behavior and both query shortcuts. Every clause carries actionable content.

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 9-parameter, zero-annotation, no-output-schema list tool, the description covers the essentials and even enumerates the return fields, which substitutes for a missing output schema. Pagination semantics across pages are the one omission.

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 56%, and the description fills much of the gap: it explains both boolean flags, and gives concrete Vikunja filter syntax examples (`done = false && due_date < now+7d`, `labels in 3, 5`) that go well beyond the schema's one-line field list. page, perPage, sortBy, orderBy and search are left to the schema, which documents them adequately.

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 and resource with scope ('across all projects or within one project'), and explicitly carves out what it does not return, routing agents to the sibling get_task for descriptions. An agent can distinguish it from get_task and the mutation siblings without opening any 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?

Gives concrete usage conditions: default open-only behavior, assignedToMe=true for the current user, and raw filter strings for advanced queries with worked examples. It names get_task as the alternative for full task detail, though it does not state when a caller should prefer search or when filters should be avoided.

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