View Template Info

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

With no annotations, the description carries the full burden and does well: it discloses error behavior (unknown view returns the site's views, unknown display_id returns that view's displays), the fallback chain, and the in_checked_theme marking conditioned on being able to read the default theme's templates via DRUPAL_ROOT. It also explains why the JSON:API collection is the stable source across Drupal naming generations. Missing only explicit read-only/permission notes, but the disclosure is rich.

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 purpose statement is front-loaded and every block adds real information about lookup, fallback, and errors. The second paragraph is a single very long multi-clause sentence, which slightly hurts scanability, but there is little filler to cut.

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?

An output schema exists, so return-value format is covered elsewhere, and the description fills in the behavioral gaps an agent needs: lookup semantics, fallback ordering, and both error cases. It stops short of documenting permissions or limits, but for a read-only lookup tool with a companion output schema this is close to complete.

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 0%, so the description must compensate, and it largely does: it identifies view_name as the machine id (drupal_internal__id) and explains how display_id changes the result set (chain starts at views-view--NAME--DISPLAY with fallback to the whole view, vs. an entry per display when omitted). It adds genuine semantics beyond the bare schema types, though it doesn't spell out exact string formats or error semantics per param in a structured way.

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 opening line names a specific resource ('Template names for overriding a Views display') and adds scoping via 'verified against the site,' so an agent knows it returns Views override template candidates rather than generic suggestions. It stops short of naming sibling tools like theme_template_overrides or template_suggestions, so it doesn't differentiate explicitly. A clear verb+resource would push this to a 5.

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 implicitly teaches usage through the two invocation modes (with vs. without display_id and how the chain differs), which is meaningful. However, it never states when to prefer this over sibling tools that also surface template names, nor any prerequisite/context for choosing it. Usage is inferable rather than stated.

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