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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real context beyond them: the reason is persisted in the account, must be carried into the final report, and a discard is a judgment rather than evidence. "Le pagine già lette restano lette" clarifies the state semantics that the readOnlyHint alone leaves ambiguous. It stops short of saying what a rejected or duplicate discard call returns, which keeps it off a 5.

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 action and the qualifying condition, then the constraints. The three examples are illustrative rather than filler, though they occupy a large share of a fairly dense paragraph that could be tightened slightly.

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?

Output schema exists, so return values need no explanation. For a 3-param mutation of research state with annotations covering safety, the description covers the eligibility rule, size limits, reason format, persistence, and reporting obligation — everything needed to call it correctly.

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 0%, so the description carries the burden and largely does: it adds the 3-300 character constraint on motivo (absent from the schema), the 500-item ceiling on pagine, and the requirement that pagine come from the already-listed pages. The piano parameter, however, is never explained in either place.

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 ("Scarta pagine dell'elenco") plus the exact condition that qualifies it ("che la riga basta a escludere"), and the required reason. It also names the sibling it is not — research_read — for the ambiguous case, so an agent can distinguish it without opening either 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 (the index row alone is enough to exclude), explicit when-not-to ("Nel dubbio leggere con research_read"), and explicit preconditions (only pages already shown in the list, up to 500 numbers per call). This is a full routing rule, not an implied one.

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