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

Annotations already cover the read-only, non-destructive, closed-world profile, and the description adds substantial context beyond them: serial is capped at 16 KiB and reset at each compile, events are capped at 2000, circuit_error is 'returned once', circuit_modified is null when unknown. It does not cover pagination or cost of repeated polls, but the behavioral disclosure is unusually rich for a read tool.

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?

No sentence is pure filler — each one describes a distinct returned field or constraint — but there is no front-loaded summary sentence; the text starts with a parenthetical and reads as a dense, unterminated field dump, making it hard to scan for the one routing rule it contains.

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 output schema, the description justifiably spends most of its length documenting return values, and it does so thoroughly (bench mode, challenge mode, circuit_modified, circuit_error). But it leaves the auth-ish `agent_token` unexplained and never positions the tool against its many siblings, so it is not fully complete for correct invocation.

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 description coverage is 0%, so the description must carry all three parameters. It handles since_ms well (events window, 2000 cap) but says nothing about `session` or `agent_token`, the latter of which looks like an auth/identity parameter that materially affects invocation.

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 description never states a clean verb+resource; it opens mid-thought with 'Last state (with circuit, the browser's components and wires), last compilation and the events after since_ms' — effectively a catalogue of returned fields. An agent can infer this reads simulation state, but nothing distinguishes it from siblings like bench_snapshot, read_capture or session_status.

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?

One explicit preference is given: 'prefer it over reconstructing serial from `events`', which is a genuine routing rule. The since_ms window ('2000 at most') implies polling usage, but there is no guidance on when to choose this over bench_snapshot or read_capture, and no prerequisites stated.

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