Update task

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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description does add real context beyond them with 'guarded by its etag' and the raw WebDAV path, but it omits the crucial partial-update semantics: whether an omitted or null field leaves the value untouched or clears it, and what happens on an etag mismatch.

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?

Two tight lines with the mutation scope front-loaded and no filler. The raw PUT path with {user}/{calendar}/{object} placeholders is somewhat redundant against the single task_url parameter and could momentarily confuse an agent about which identifiers to supply.

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 six-parameter mutation tool with zero schema descriptions and no output schema, the description is too thin: it never explains the update payload, partial-vs-full update behavior, or the return/error shape. Annotations carry the safety story, but the calling contract for the optional fields is left entirely to inference.

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% across six parameters, so the description must carry the burden and largely does not. It hints at the 'completed' flag via 'mark it complete or open again' and implies task_url via 'one task', but says nothing about summary, due, description, percent_complete, their accepted formats, or what the null defaults mean.

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 ('Change one task') and covers the special cases of completing or reopening it, which an agent can distinguish from nextcloud_create_task and nextcloud_delete_* siblings. It stops short of explicitly naming a sibling or delimiting itself from nextcloud_update_event / nextcloud_update_card.

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?

Use is only implied: 'Change one task, or mark it complete or open again' signals a mutation of an existing task, and the presence of task_url implies the task must already exist. There is no guidance on prerequisites (where to obtain task_url, e.g. from nextcloud_list_tasks), no when-not-to-use, and no alternative named.

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