Create saved view

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

Annotations already cover the read/write profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false). The description adds useful behavioral context: the saved view appears in the user's sidebar and filter_rules rely on numeric web UI rule types. It does not mention duplicate-name behavior or the return payload, but it adds enough context beyond the annotations.

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 sentences, no filler. The first states the tool's purpose; the second flags the key gotcha and points to get_saved_view. Strong front-loading and every sentence carries weight.

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 create tool with seven parameters and no output schema, the description covers the one genuinely tricky aspect (filter_rules) and explains the expected user-visible effect (appears in sidebar). It does not describe the return value or repeated-call behavior, but those are unlikely to block correct invocation. It is sufficiently complete for selection and basic use.

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 only 14%, so the description must compensate. It does meaningfully explain the most complex parameter, filter_rules, with the advice to copy an existing view's shape from get_saved_view instead of guessing. However, other parameters like page_size, sort_field, sort_reverse, show_in_sidebar, and show_on_dashboard are left entirely to the schema/type/name, so compensation is only partial.

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 uses a specific verb and resource: 'Save a filter preset that shows up in the user's Paperless sidebar.' This clearly indicates the tool creates a user-facing saved view. However, it does not explicitly contrast with update_saved_view or list_saved_views, and the verb 'Save' could ambiguously imply either create or update without the tool name carrying that weight.

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 gives concrete, actionable guidance: 'copy the shape from an existing view via get_saved_view rather than guessing.' This tells the agent exactly how to obtain valid filter_rules and identifies get_saved_view as the source. It does not, however, state when to use this tool versus update_saved_view or other siblings, so exclusions are not explicit.

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