wpf_report

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

No annotations are provided, so the description carries the full burden and does substantial work: it declares the operation is non-mutating ('does not change the UI'), discloses a significant limitation ('does not realize virtualized items'), and states that output includes coverage and truncation reasons. Remaining gaps are permissions/attach prerequisites and rough cost of a process-wide trace scan.

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 with the purpose, then limits, then behavioral caveats — a sensible ordering with no filler. It is dense to the point of terseness ('State counts are observations, not defects'), requiring some parsing, but every sentence carries information.

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?

With no annotations and no output schema, the description covers the essentials an agent needs: scope, bounds, non-mutation, truncation reporting, and the interpretive caveat about state counts. It stops short of describing the report's shape (sections, per-element vs aggregate counts), which matters for a multi-section diagnostic payload.

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% with four parameters, so the description must compensate. It does give usable bounds for three of them (max_elements 1-2000, max_depth 1-100, max_findings 1-500), which is real added value, but root_handle is only obliquely implied by 'or a subtree' and its null default/format is never explained.

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?

States a specific verb and resource ('Collect a bounded diagnostic report') plus the scope ('across open windows or a subtree') and enumerates what the report contains: binding/validation errors, state counts, and process-wide binding traces. This clearly distinguishes it as an aggregate report rather than a single-purpose call, though it never names the siblings it overlaps with (e.g. wpf_get_binding_errors, wpf_snapshot).

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 'across open windows or a subtree' phrasing implies scope selection but never states the condition explicitly (that omitting root_handle targets all windows). No guidance on when to prefer this over wpf_get_binding_errors, wpf_get_visual_tree, or wpf_snapshot, which cover overlapping territory.

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