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

With readOnlyHint already covering safety, the description still adds substantial context: no account or token is needed, the response includes provenance fields (source, original URL, license, SHA-256, depositing agent), and it flags that third-party text arrives under `contenuti_di_terzi` and must be treated as untrusted data rather than instructions. That prompt-injection warning is exactly the kind of behavioral disclosure the agent cannot get from annotations.

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-loads the core action, then uses labeled 'When to use', 'Notes', and 'Example arguments' blocks so each sentence is scannable and purposeful. The field enumeration is long but earns its place because no output schema exists.

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 and a single required parameter, the description carries and discharges the burden: it enumerates returned fields, explains the untrusted-content caveat, and states the auth requirement. 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 100%, so the id format and length are already documented, giving a baseline of 3. The description goes further by supplying a concrete example argument and tying the id's origin to search_archive results, which helps the agent construct a valid call.

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 ('Return the stored text of one archive document') and immediately qualifies the scope ('often an abstract or extract, not the full original publication'), which prevents the agent from expecting full text. It is clearly separable from search_archive by the singular document id.

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 says 'Use after search_archive, with a document id from its results, when the snippet is not enough or you need to quote and cite the source' — a clear trigger condition plus the source of the required id. However, the sibling cite_document directly overlaps with the 'quote and cite' motivation and is never mentioned, so the read-vs-cite choice is left to inference.

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