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

Annotations already declare openWorldHint=true and destructiveHint=false, but the description adds substantial unannotated behavior: the challenge/anti-abuse handshake, per-network and node-wide daily budgets, and the important fallback that a limit hit returns a *previous* verified run marked status: cached rather than a new replay. That caching disclosure prevents an agent from misreporting a stale result as fresh.

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 purpose and constraints, then flow, then limits, then the sibling pointer — a sensible order. It is semicolon-dense and longer than typical, but each sentence (challenge flow, caching fallback, limits, alternative tool) carries information an agent needs, 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?

With no output schema, the description takes on the return contract and does so: run_id, run page, poll hint, run_record cid + verify_record, and the cached-status variant. For a two-phase, rate-limited, open-world tool this covers everything needed to call and interpret results.

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 100%, so baseline is 3; the description earns above that by explaining the relationship between challenge_id and answer (two-phase flow) and when wait_seconds matters (blocking vs. returning run_id right away). It doesn't add format/syntax detail for the nested inputs map beyond what the schema says.

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 ("Runs a real browser replay on a public site") plus the constraint envelope (capped, non-destructive allowlisted skills). It explicitly distinguishes itself from the sibling run_skill ("For your own uncapped runs use run_skill in the local server"), so an agent can route without opening a schema.

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?

Gives the exact two-call protocol (first call returns challenge_id, second call submits slug+inputs+challenge_id+answer), names the alternative tool for uncapped runs, and names verify_record as the follow-up for the returned cid. Prerequisites (no token/identity needed) and the limit-reached fallback path are both spelled out.

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