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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description adds real value by disclosing the return payload traits (SHA-256 per version, EAS attestation anchored on Base) and the important limitation that only previously analysed domains are covered. Short of 5 because error behavior for unknown domains is not stated.

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?

Two dense sentences plus a constraint sentence, front-loaded with what the tool returns and followed by the mode-selection rule. The parenthetical list of document types and the hash/attestation detail are load-bearing rather than filler. Slightly heavy in the first sentence but no wasted text.

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 an output schema present, the description needn't document return structure, and it still summarizes the key payload facts. It covers the mode switch, the timestamp semantics, and the domain-corpus limitation. The only gap is behavior when the domain is unknown or the timestamp predates any record.

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 the baseline is 3, but the description genuinely adds semantics the schema does not: `source` acts as a mode switch (index vs. full document) and `at` selects the instant whose in-force version is returned. It also decodes the enum value 'portada' as homepage headers. That is real value beyond the structured fields.

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States a specific verb-and-resource pair: retrieves the historical content of a domain's robots.txt/llms.txt/tdmrep.json/RSL/homepage headers at a given instant, including version hashes and attestations. It is clearly a read/lookup operation distinct in kind from the consent-scoring siblings, though it never names a sibling or explicitly contrasts itself with them.

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?

Explicitly explains the two calling modes — omit `source` to get the version index, supply `source` (plus optional `at`) to get the document in force at that instant — which effectively tells the agent when to use which shape of call. The precondition 'Covers only domains already analysed' is a genuine usage constraint. It stops short of naming an alternative tool for un-analysed domains.

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