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

Annotations only cover the safety profile (readOnly/openWorld/idempotent/non-destructive), so the description carries real extra weight and delivers: the full-text index lags the crawl by years, coverage is biased toward the Portuguese web while some international English sites are included, and hit magnitudes for sample probes. That materially changes how an agent interprets results. It stops short of 5 only because it gives no operational behavior details such as truncation or rate limits.

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, then when-to-use, then capability and caveats in a single dense block with no filler sentences. It is longer than strictly necessary — the three probe queries with estimated hit counts stretch the definition — but each sentence still carries usable information.

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 compensates by enumerating the per-hit return fields (title, original URL, capture date, matching snippet, replay URL, extracted-text and screenshot links) along with coverage and index-staleness caveats. An agent has everything needed to call it and interpret the response.

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 100%, so every parameter is already documented upstream (including the 'omit to unless you need a window' caveat and the offset/next_offset paging note). The description largely restates supported filters (date window, site, file type, minus-exclusion, offset) plus one worked exclusion example ('Albert -Einstein'), which adds marginal but not substantial meaning.

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 (full-text search of archived pages in Arquivo.pt) and immediately names the sibling it must not be confused with (arquivo_url_history for known/current URLs). An agent can distinguish it from arquivo_page_text and arquivo_url_history without opening any 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?

Explicit when-to-use ('when the URL is unknown'), explicit alternatives ('use arquivo_url_history for anything recent at a known URL'), and an explicit anti-pattern ('Do not pass a URL as the query'). This is the strongest form of routing guidance.

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