task_list

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

No annotations are supplied, so the description carries the full burden. It does disclose one important non-obvious behavior: results silently exclude closed tasks unless status or include_closed is set, and it explains that filters are ANDed and that q searches specific fields. It says nothing about result ordering, default page size, or how limit/offset behave, which matters for a listing tool with no output schema.

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 default-scope caveat is front-loaded in the first clause, and the filter list is dense with zero filler. The telegraphic parenthetical style ("AND", "no update in N hours") is efficient but slightly compressed, and the filter enumeration is not ordered by importance.

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 10-parameter read tool with no annotations and no output schema, the description covers 8 of the 10 filters well but omits pagination (limit/offset) and says nothing about what a result looks like or how results are ordered. An agent could call it correctly for filtering, but would be guessing on paging and on the overlap with task_stale/task_waiting.

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 0%, so the description must compensate and it largely does: it defines status as a single value or comma list with a concrete example, due_before as ISO date, stale_hours as "no update in N hours", and enumerates the fields q searches (title/done_means/notes/links). The notable gap is limit and offset, which are never mentioned even though pagination semantics are exactly what the bare schema fails to convey.

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?

Opens with a specific verb+resource ("List tasks") and immediately qualifies the default scope, which tells an agent this is a read/enumerate tool rather than a create or mutate one. It does not name sibling alternatives such as task_stale or task_waiting, which look like they overlap with the overdue/stale filters, so sibling differentiation is only partial.

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?

The description states the default behavior clearly ("open only unless status or include_closed given"), which is effectively a when-to-use rule for closed vs open tasks. It gives no guidance on when to pick this tool over task_stale, task_waiting, or task_get, even though the overdue/stale_hours filters imply overlap with those siblings.

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