web_audit

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the '[INSPECT] Read-only' label largely restates structured data. The description does add one genuinely useful behavioral fact beyond the annotations: 'Each finding has a concrete fix.' It says nothing about result format, aggregation, or cost of running the audit.

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?

Compact and front-loaded: the '[INSPECT] Read-only' classification leads, followed by a scoped list of inspected dimensions and a closing note on fixes. The long comma-separated enumeration is dense but each item is a distinct check, so little is wasted.

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 zero-parameter, read-only diagnostic with no output schema, the description covers both what is inspected and what findings contain ('Each finding has a concrete fix'), which is close to sufficient. It stops short of describing the return structure or how findings are grouped, but the scope is otherwise 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?

The tool takes zero parameters (empty schema, no required fields), so there are no parameter semantics to explain. Baseline 4 applies; the description has no parameters to compensate for.

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+resource: a read-only 'website health check' that inspects pixel ratio, canvas resize, rendering costs, textures, shadows, color space, and draw calls. The scope is concrete and enumerable, though it overlaps several siblings (performance_snapshot, draw_call_breakdown, memory_stats, texture_list) without explicitly distinguishing itself from them.

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 '[INSPECT] Read-only' tag and 'health check' framing imply a diagnostic context, but there is no explicit when-to-use versus alternatives like performance_snapshot or draw_call_breakdown, nor any exclusions or prerequisites. Guidance is left entirely to inference.

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