capture_summary

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds one genuinely useful behavioral trait — that only the 100 most frequent call ids are returned out of calls_total, i.e. the output is truncated — but says nothing about error behavior, cost, or how much of the trace is actually parsed.

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?

A single front-loaded sentence with no filler; the key scope ('without Xcode') and the contents appear immediately. The trailing enumeration is dense but each item earns its place.

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 values need not be spelled out, and annotations cover the read-only profile; with a single fully documented parameter the definition is nearly complete. The remaining gap is sibling disambiguation against capture_records, which matters given the crowded tool list.

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?

Only one parameter and schema description coverage is 100%; the schema already explains that 'capture' is a path to a .gputrace bundle inside METAL_TRACE_OUT or METAL_TRACE_READ. The description adds nothing about the parameter beyond the resource type, so baseline 3 applies.

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?

Names a specific verb (Reads) and resource (Metal .gputrace capture) and enumerates exactly what the summary contains: command buffers, encoders, draws, debug groups, top-100 call ids. It does not, however, contrast itself with the sibling capture_records, so an agent must infer which capture-reading tool to pick.

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 phrase 'without Xcode' hints at the lightweight/headless use case, but there is no explicit when-to-use, no when-not-to-use, and no reference to the obvious alternative capture_records. The agent gets no routing guidance.

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