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

Annotations only give the generic write profile; the description adds real operational behavior: columns/filters are applied atomically, an invalid columnIdentifier or filter shape rolls back with 400, a 201 therefore guarantees a fully configured view, and no `columns` means defaults-only/effectively empty. It also discloses the required `views:write` scope, which no annotation covers.

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?

Front-loaded and mostly dense, with the critical columns warning placed early. Minor waste: the type enum is restated verbatim from the schema, and the columns mistake is asserted twice ('ALWAYS pass columns...' followed by 'This is the most common mistake here').

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?

Covers type selection, column configuration, atomicity/error semantics, discovery of identifiers, and auth scope — enough for a 12-param create tool with no output schema. It never explains what `scope` vs `scopeIdentifier` mean or how sortBy/sortDirection/isPrivate interact with the created view, which leaves a real hole for a create with scope-relative targeting.

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 42%, and while the description adds genuine meaning for `columns` (list order is display order, omitted columns are hidden, atomic validation) much of that is already echoed in the schema's own param description. The other undocumented parameters — scope, scopeIdentifier, sortBy, sortDirection, isPrivate, workspace — get no explanation in the description, so the gap is only partly compensated.

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 ('Create a view') and immediately enumerates the supported view types, so the agent knows exactly what object is produced. It also distinguishes itself from pm_update_view by steering primary-view configuration there rather than duplicating it.

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?

Explicitly states when not to use it ('prefer configuring its auto-created primary view with pm_update_view; add another view only for a distinct workflow') and names a prerequisite discovery call (pm_get_workspace_context) for unknown column identifiers. Both the alternative and the escalation path are spelled out.

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