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

Beyond the readOnlyHint/openWorldHint annotations, it discloses the default result scoping, the ordering rule, that categories are included, and a prompt-injection caution that text fields are user data rather than instructions. What it omits is pagination/overflow behavior around the limit parameter and any indication of result size.

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?

Four short sentences, front-loaded with purpose and ordering, then defaults, then return type, then the safety note. The parenthetical about appointment start vs window dueAt is dense but earns its place; nothing is redundant.

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 four-parameter read tool with no output schema, it covers purpose, default filtering, ordering, and injection safety, which is most of what an agent needs. It is still incomplete on the meaning and bounds of limit and categoryId, and it does not sketch the JSON shape beyond "Returns JSON".

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 only 25% (only dueBefore is described in the schema), but the description compensates partially by explaining what an absent status filter means and how dueAt/start drive ordering. It says nothing about limit (default 50, max 200) or categoryId, so two parameters remain undocumented in both places.

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 names a specific verb and resource ("List the user's tasks") and adds sort semantics (soonest first, appointment by start, window by dueAt) plus the fact that categories are joined in. It stops short of distinguishing itself from the sibling search_tasks, so an agent cannot tell from the text alone when listing beats searching.

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 gives one genuinely useful usage rule: without a status filter only open work (inbox, open, waiting) is returned, which tells the agent how to get done/dropped items. There is no explicit when-to-use/when-not guidance relative to search_tasks or get_task, leaving the choice of sibling to inference.

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