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

Annotations already say this is a non-read-only, non-destructive, open-world mutation, and the description goes well past that: ~30 second runtime, serialized execution, 5-per-scan daily cap, plan gating with an on-Free error, and the visible side effect that fixed items get ticked off. That is exactly the operational context an agent needs before invoking a mutating, paid-tier 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?

Front-loaded with the trigger and the action, and each later sentence (results vocabulary, plan gating, throttle, exclusions) carries real information. It is dense and parenthetical-heavy ('(on Free it returns an error that says so)', 'no scan from the limit and no AI'), which reads as slightly compressed rather than wasteful.

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 steps up and declares the return vocabulary (fixed, improved, still_open, visual_check) plus where results surface (get_actions, report page). Combined with the runtime and rate-limit disclosure, an agent has everything needed to call it correctly and interpret the result.

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 50%: page_url is documented ('the page of an item in get_actions') while scan_id is bare, and the description never clarifies scan_id's provenance or format beyond the loose phrasing 'one page of a scan'. Baseline 3 is appropriate since the description only implies the page-belongs-to-scan relationship rather than adding semantics the schema lacks.

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 ('load one page of a scan again (phone and desktop) and run the same checks') plus the trigger condition ('After the owner publishes a change'), so an agent can tell it apart from get_actions, get_report or scan_site without opening a schema. It also names its out-of-scope territory explicitly (speed and site-wide items).

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 an explicit when (after the owner publishes a change), explicit when-not (speed and site-wide items, AI search, facts across pages), and names the alternatives for those cases (mark_done, or a new scan for speed). The one-at-a-time / 5-per-day throttle and the Pro/Lifetime gating further tell the agent when the call will fail.

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